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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Parl
    -0.07
    early
    -0.07
    ciler
    -0.06
     cougar
    -0.06
    CN
    -0.06
     ={↵
    -0.06
    ]()↵
    -0.06
    BT
    -0.06
     ivory
    -0.06
     Com
    -0.06
    POSITIVE LOGITS
    确认
    0.08
    _BUILD
    0.07
    �
    0.06
    距離
    0.06
    년에는
    0.06
    _play
    0.06
    结束
    0.06
    )&&(
    0.06
    рави
    0.06
     важно
    0.06
    Act Density 0.000%

    No Known Activations