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

    Neuronpedia

    INDEX
    Explanations

    terms related to mathematical derivatives and probabilities in a statistical context

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

    Fractions and mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    years and locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     &___
    -0.61
    :{
    -0.59
     */
    -0.58
     {
    -0.58
    ọi
    -0.58
    rungsseite
    -0.53
     iconFacebook
    -0.52
    *}\
    -0.51
    amal
    -0.51
     bezeichneter
    -0.50
    POSITIVE LOGITS
    こちらも
    0.81
    sidemargin
    0.74
     opět
    0.74
     επίσης
    0.66
    again
    0.65
     again
    0.63
    出版年
    0.62
    oneofs
    0.61
     szint
    0.60
    ритори
    0.60
    Act Density 0.716%

    No Known Activations