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

    Neuronpedia

    INDEX
    Explanations

    Hiring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    确实是
    -0.07
    텍
    -0.07
    デン
    -0.07
    臨
    -0.06
    競爭
    -0.06
    TOP
    -0.06
     lul
    -0.06
    ัส
    -0.06
    一边
    -0.06
    饮料
    -0.06
    POSITIVE LOGITS
    fully
    0.08
    register
    0.08
     Relay
    0.07
    receiver
    0.07
     DefaultValue
    0.07
    .getParam
    0.07
    JS
    0.07
    @Module
    0.07
     ORDER
    0.07
    _password
    0.07
    Act Density 0.041%

    No Known Activations