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

    Neuronpedia

    INDEX
    Explanations

    behavioral reinforcement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    regex
    -0.07
    _indicator
    -0.07
    lasses
    -0.06
    Objective
    -0.06
    _classifier
    -0.06
     imprimir
    -0.06
    違い
    -0.06
    progressbar
    -0.06
    NDER
    -0.06
     hostage
    -0.06
    POSITIVE LOGITS
     Strikes
    0.07
    .fhir
    0.06
     Shen
    0.06
    �
    0.06
    venth
    0.06
    ảy
    0.06
     bỏ
    0.06
     wow
    0.06
    염
    0.06
    amura
    0.06
    Act Density 0.021%

    No Known Activations