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

    Neuronpedia

    INDEX
    Explanations

    phone numbers

    oai_token-act-pair · gemini-2.0-flash

    tokens containing special character patterns

    np_token-act-pair-logits · gpt-4o-mini

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WireFormatLite
    -0.81
    AndEndTag
    -0.80
     препратки
    -0.75
    AddHtmlAttribute
    -0.73
     &___
    -0.73
    __(/*!
    -0.73
    findpost
    -0.72
     defaultstate
    -0.71
    FieldBuilder
    -0.71
    ]--;
    -0.68
    POSITIVE LOGITS
     ejec
    0.54
     jurí
    0.53
     judiciales
    0.50
     arché
    0.49
     itſelf
    0.48
     alimentare
    0.47
     Hauteur
    0.47
     maaaring
    0.47
     wif
    0.46
     PIA
    0.46
    Act Density 0.490%

    No Known Activations