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

    Neuronpedia

    INDEX
    Explanations

    structured data related to experimental results and statistics

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

    quantitative measures and results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dirinya
    -0.49
    Tikang
    -0.46
     života
    -0.44
     život
    -0.43
     generaciones
    -0.42
     democrática
    -0.42
     sebou
    -0.42
     menye
    -0.41
     compartido
    -0.41
     swój
    -0.41
    POSITIVE LOGITS
    TagMode
    0.76
    IntoConstraints
    0.75
     Roskov
    0.70
     Exacts
    0.65
    ьаж
    0.59
    FunctionFlags
    0.57
    transQ
    0.53
    ----</
    0.52
    rungsseite
    0.52
     للمعارف
    0.51
    Act Density 0.207%

    No Known Activations