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

    Neuronpedia

    INDEX
    Explanations

    numeric values and version specifications related to software or libraries

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

    Version numbers

    np_acts-logits-general · gemini-2.0-flash

    version numbers and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bew
    -0.53
     at
    -0.51
     l
    -0.49
     assume
    -0.48
    kwds
    -0.48
    RenderAtEndOf
    -0.48
    vaadin
    -0.45
     respon
    -0.44
     su
    -0.44
     di
    -0.44
    POSITIVE LOGITS
    ագրություններ
    0.87
     Efq
    0.85
     myſelf
    0.83
     nakalista
    0.83
     Monfieur
    0.78
     itſelf
    0.78
     neceff
    0.75
    yntaxException
    0.73
     himſelf
    0.72
     faſt
    0.72
    Act Density 0.241%

    No Known Activations