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

    Neuronpedia

    INDEX
    Explanations

    conduct

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     FAST
    -0.07
     Salad
    -0.07
    été
    -0.06
    금
    -0.06
    -css
    -0.06
    ذر
    -0.06
    ковий
    -0.06
     jeho
    -0.06
    htt
    -0.06
    VICE
    -0.06
    POSITIVE LOGITS
    conduct
    0.07
    <strong
    0.07
    〜
    0.07
     характеристики
    0.07
     BIN
    0.06
    otify
    0.06
     otel
    0.06
    CNT
    0.06
     tweets
    0.06
     val
    0.06
    Act Density 0.002%

    No Known Activations