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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -La
    -0.08
     rôle
    -0.08
     accessible
    -0.08
    侉
    -0.07
    globals
    -0.07
     persists
    -0.07
    Almost
    -0.07
    焊接
    -0.07
    xCF
    -0.07
     getUsername
    -0.07
    POSITIVE LOGITS
     istediği
    0.07
     mag
    0.07
    悪い
    0.06
    LIKELY
    0.06
    drop
    0.06
    ('',
    0.06
    ерт
    0.06
    .FLAG
    0.06
     pix
    0.06
    买卖
    0.06
    Act Density 0.005%

    No Known Activations