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

    Neuronpedia

    INDEX
    Explanations

    legal background information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adolescents
    -0.07
    although
    -0.07
     ];↵↵
    -0.06
    س
    -0.06
     SCHOOL
    -0.06
    以为
    -0.06
     ];↵
    -0.06
    .getAddress
    -0.06
    ];↵↵
    -0.06
    .writeString
    -0.06
    POSITIVE LOGITS
     olur
    0.08
    HQ
    0.07
    /component
    0.07
     Baths
    0.06
     slap
    0.06
     Runtime
    0.06
     eup
    0.06
     scouting
    0.06
     saddle
    0.06
     tách
    0.06
    Act Density 0.003%

    No Known Activations