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

    Neuronpedia

    INDEX
    Explanations

    publishing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pay
    -0.06
     emergence
    -0.06
     答
    -0.06
     품
    -0.06
    기를
    -0.06
     RD
    -0.06
    ΩΤ
    -0.06
     charging
    -0.06
    SOAP
    -0.06
    aupt
    -0.06
    POSITIVE LOGITS
     Eternal
    0.07
     prostřed
    0.07
     adres
    0.07
     выбра
    0.07
    Shock
    0.07
    산업
    0.06
    StatusLabel
    0.06
    =L
    0.06
    сли
    0.06
    Som
    0.06
    Act Density 0.020%

    No Known Activations