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

    Neuronpedia

    INDEX
    Explanations

    larvae

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dever
    -0.07
    :)];↵
    -0.06
    ス
    -0.06
    ?v
    -0.06
     stato
    -0.06
    　イ
    -0.06
     города
    -0.06
     Seç
    -0.06
    есь
    -0.06
    ya
    -0.06
    POSITIVE LOGITS
    /window
    0.07
     Tahoe
    0.06
     신입
    0.06
     Cambridge
    0.06
    emit
    0.06
     RX
    0.06
    اقل
    0.06
     更新
    0.06
    _PANEL
    0.06
     Leonard
    0.06
    Act Density 0.004%

    No Known Activations