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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     partnership
    -0.07
    _PRIV
    -0.06
     การ
    -0.06
     snowy
    -0.06
    (Socket
    -0.06
     rises
    -0.06
     tips
    -0.06
    .Rec
    -0.06
    ientras
    -0.06
    N
    -0.06
    POSITIVE LOGITS
    Lake
    0.07
     therapeutic
    0.07
     درد
    0.07
     ресурс
    0.06
     Effective
    0.06
    /releases
    0.06
    Gram
    0.06
     Gram
    0.06
     Thema
    0.06
    >Email
    0.06
    Act Density 0.054%

    No Known Activations