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

    Neuronpedia

    INDEX
    Explanations

    asterisk

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _legal
    -0.07
    _txt
    -0.07
    纯洁
    -0.07
    บาด
    -0.07
    SESSION
    -0.06
     Attend
    -0.06
    logout
    -0.06
    ethical
    -0.06
     reacting
    -0.06
     Helvetica
    -0.06
    POSITIVE LOGITS
     Dolphin
    0.08
     Anthem
    0.07
    ói
    0.07
    大豆
    0.07
     tease
    0.07
     opr
    0.07
    .term
    0.06
    亲近
    0.06
    드리
    0.06
    _unregister
    0.06
    Act Density 0.000%

    No Known Activations