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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Given
    -0.08
    فن
    -0.07
    噂
    -0.07
    Dr
    -0.07
     feel
    -0.07
     mümkün
    -0.07
     pomysł
    -0.07
    _booking
    -0.06
    byn
    -0.06
    mando
    -0.06
    POSITIVE LOGITS
    >New
    0.08
    嚎
    0.07
    -black
    0.07
    orde
    0.07
    =".
    0.07
     RS
    0.07
    签名
    0.07
     dense
    0.07
    .keywords
    0.06
    嘶
    0.06
    Act Density 0.250%

    No Known Activations