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

    Neuronpedia

    INDEX
    Explanations

    string

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UN
    -0.08
     Oh
    -0.06
    SCAN
    -0.06
     Grace
    -0.06
    IGO
    -0.06
    ech
    -0.06
    CLE
    -0.06
     Sai
    -0.06
    ubb
    -0.06
    'an
    -0.06
    POSITIVE LOGITS
    유머
    0.07
    startsWith
    0.06
     smo
    0.06
    
    0.06
    มากกว
    0.06
    getStatusCode
    0.06
    .mods
    0.06
    paněl
    0.06
     olmuş
    0.06
    为空
    0.06
    Act Density 0.140%

    No Known Activations