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

    Neuronpedia

    INDEX
    Explanations

    Open parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     variance
    -0.06
    opens
    -0.06
    "],
↵
    -0.06
    ]")↵
    -0.06
    藤
    -0.06
     God
    -0.06
     материалов
    -0.06
     الملك
    -0.06
    $rs
    -0.06
    ]})↵
    -0.06
    POSITIVE LOGITS
     adapted
    0.07
    任
    0.07
    esper
    0.06
     Biz
    0.06
     Gi�
    0.06
     Ген
    0.06
    LOAT
    0.06
    ichtet
    0.06
    aurants
    0.06
    0.06
    Act Density 0.002%

    No Known Activations