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

    Neuronpedia

    INDEX
    Explanations

    alcohol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heroes
    -0.07
    then
    -0.07
     Royals
    -0.07
    ADING
    -0.06
    始
    -0.06
     Prosecutor
    -0.06
    Driver
    -0.06
     Gun
    -0.06
     Disney
    -0.06
    ponent
    -0.06
    POSITIVE LOGITS
     EACH
    0.06
     клу
    0.06
    اين
    0.06
     sanctioned
    0.06
     İran
    0.06
     Yugosl
    0.06
     NONINFRINGEMENT
    0.06
    (Integer
    0.06
    .ImageIcon
    0.06
    ่ต
    0.06
    Act Density 0.015%

    No Known Activations