Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to risks, safety issues, and the detailing of various influencing factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by descriptive information

    np_acts-logits-general · gemini-2.0-flash

    other information categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    intahan
    -0.51
    GeoNames
    -0.49
     themſelves
    -0.46
    AutoScaleMode
    -0.44
    ulemon
    -0.41
    ArgsConstructor
    -0.41
     itſelf
    -0.40
    ➋
    -0.40
    GeneratedValue
    -0.39
     виправивши
    -0.38
    POSITIVE LOGITS
     besides
    0.75
     similarly
    0.71
     than
    0.68
     equally
    0.59
    besides
    0.57
    worldly
    0.56
    WebElementEntity
    0.54
     similar
    0.54
     Similarly
    0.54
    同様に
    0.51
    Act Density 0.440%

    No Known Activations