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

    Neuronpedia

    INDEX
    Explanations

    terms indicating specifications or requirements

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

    given or specified argument

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.51
    AnimationsModule
    -0.46
     ſon
    -0.45
     themſelves
    -0.45
    reszcie
    -0.43
     leſs
    -0.43
    kadot
    -0.43
     auroit
    -0.43
     niitä
    -0.43
     himſelf
    -0.43
    POSITIVE LOGITS
    Specified
    0.44
    specified
    0.44
    Configured
    0.43
    Selected
    0.43
    قایناقلار
    0.42
     указа
    0.42
     peo
    0.41
    Remaining
    0.41
    maining
    0.41
    ない
    0.41
    Act Density 0.009%

    No Known Activations