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

    Neuronpedia

    INDEX
    Explanations

    Nearest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ball
    -0.07
    対応
    -0.07
    isks
    -0.06
    陸
    -0.06
     жовтня
    -0.06
     regul
    -0.06
     shale
    -0.06
    sov
    -0.06
     Proceedings
    -0.06
     causal
    -0.06
    POSITIVE LOGITS
    $req
    0.07
    _response
    0.06
    操作
    0.06
    کم
    0.06
    filters
    0.06
    تر
    0.06
    嘴
    0.06
    .eu
    0.06
    $return
    0.06
    submitted
    0.06
    Act Density 0.000%

    No Known Activations