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

    Neuronpedia

    INDEX
    Explanations

    unethical behavior

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Κο
    -0.07
     extr
    -0.07
     コ
    -0.07
     Cornel
    -0.06
    .basic
    -0.06
     ROC
    -0.06
     Serv
    -0.06
    Arc
    -0.06
    رك
    -0.06
     بسي
    -0.06
    POSITIVE LOGITS
     ilan
    0.08
    fit
    0.07
     ép
    0.07
    Fit
    0.07
    Likes
    0.06
    iferay
    0.06
     chromium
    0.06
    _CLAMP
    0.06
    장
    0.06
     bundle
    0.06
    Act Density 0.247%

    No Known Activations