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

    Neuronpedia

    INDEX
    Explanations

    Wick

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Coach
    -0.08
    caff
    -0.08
    -car
    -0.07
     Parl
    -0.07
    邨
    -0.07
     Mens
    -0.07
    .getTag
    -0.07
    ccb
    -0.06
     Ces
    -0.06
    .card
    -0.06
    POSITIVE LOGITS
     divorce
    0.07
     stray
    0.07
    ái
    0.07
     financing
    0.07
    _float
    0.07
     يصل
    0.06
    (material
    0.06
    很满意
    0.06
     yardım
    0.06
     Boo
    0.06
    Act Density 0.001%

    No Known Activations