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

    Neuronpedia

    INDEX
    Explanations

    for/in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    quota
    -0.07
    ков
    -0.07
     VIR
    -0.06
    ektor
    -0.06
     psyche
    -0.06
     shoot
    -0.06
    hlas
    -0.06
     Baz
    -0.06
    작
    -0.06
     noises
    -0.06
    POSITIVE LOGITS
     {}
↵
↵
    0.06
    Partial
    0.06
    要求
    0.06
     Chef
    0.06
    ！！
    0.06
     anticipating
    0.06
    �a
    0.06
    .RemoveAt
    0.06
     Champagne
    0.06
     Tên
    0.06
    Act Density 0.026%

    No Known Activations