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

    Neuronpedia

    INDEX
    Explanations

    suggestions and reasoning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accessory
    -0.07
     SYNC
    -0.06
    Titan
    -0.06
     TERMIN
    -0.06
     zz
    -0.06
    dd
    -0.06
     zosta
    -0.06
     COPY
    -0.06
     zest
    -0.06
     reloading
    -0.06
    POSITIVE LOGITS
    🚄
    0.07
    FileVersion
    0.07
    刊登
    0.06
     حين
    0.06
     cite
    0.06
     Gingrich
    0.06
    词条
    0.06
    첫
    0.06
     Crimea
    0.06
    蕙
    0.06
    Act Density 0.041%

    No Known Activations