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

    Neuronpedia

    INDEX
    Explanations

    code and code documentation markers like comments, semicolons, and bullets

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.70
     FetchType
    -0.66
     שוליים
    -0.64
     חיצוניים
    -0.63
     Extragalactic
    -0.63
    MessageState
    -0.60
     FontWeight
    -0.59
     saites
    -0.59
     utafitiHapana
    -0.59
    Portály
    -0.57
    POSITIVE LOGITS
     He
    0.48
    ↵↵
    0.44
     We
    0.43
     It
    0.43
     This
    0.41
    ↵
    0.41
     tratta
    0.40
    ]").
    0.40
     createState
    0.40
     A
    0.40
    Act Density 0.989%

    No Known Activations