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

    Neuronpedia

    INDEX
    Explanations

    specific technical terms and parameters associated with scientific contexts

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

    prepositions of location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.70
     myſelf
    -0.64
     ſta
    -0.64
     pleaſure
    -0.62
     anſ
    -0.61
     faſt
    -0.60
     Jefus
    -0.60
     Majefty
    -0.59
    ſelf
    -0.59
     themſelves
    -0.56
    POSITIVE LOGITS
     در
    1.49
    در
    1.12
     in
    0.91
     In
    0.84
    在
    0.79
     في
    0.75
     在
    0.75
     trong
    0.74
     în
    0.71
     ở
    0.70
    Act Density 0.000%

    No Known Activations