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

    Neuronpedia

    INDEX
    Explanations

    sexually explicit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arı
    -0.07
    ashi
    -0.06
     обще
    -0.06
     σχε
    -0.06
    Deque
    -0.06
    .AddTransient
    -0.06
    ủ
    -0.06
     CFG
    -0.06
    _barang
    -0.06
     actors
    -0.06
    POSITIVE LOGITS
    Separator
    0.07
     leveraging
    0.07
    Blocked
    0.06
    plaint
    0.06
    .Mongo
    0.06
    Critical
    0.06
     bodyParser
    0.06
    енням
    0.06
     investigated
    0.06
     BF
    0.06
    Act Density 0.014%

    No Known Activations