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

    Neuronpedia

    INDEX
    Explanations

    trusted

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Quarter
    -0.07
     evil
    -0.06
    "For
    -0.06
    ์โ
    -0.06
    -years
    -0.06
     tertiary
    -0.06
     UPLOAD
    -0.06
     Couple
    -0.06
    zoek
    -0.06
    集合
    -0.06
    POSITIVE LOGITS
    .tc
    0.07
    режд
    0.07
     симв
    0.07
     برگزار
    0.06
     hack
    0.06
     wasm
    0.06
    <|eot_id|>
    0.06
     strncmp
    0.06
    .tax
    0.06
     trusted
    0.06
    Act Density 0.009%

    No Known Activations