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

    Neuronpedia

    INDEX
    Explanations

    such

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     red
    -0.06
     dow
    -0.06
    wendung
    -0.06
     Miller
    -0.06
    miyor
    -0.06
     título
    -0.06
    /el
    -0.06
    _DEVICES
    -0.06
    .destroy
    -0.06
     Shirley
    -0.06
    POSITIVE LOGITS
    iscal
    0.07
    _BIN
    0.06
    xfc
    0.06
    termin
    0.06
    �
    0.06
    UPI
    0.06
    таж
    0.06
    ّم
    0.06
    ASN
    0.06
    สำน
    0.06
    Act Density 0.017%

    No Known Activations