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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    자기
    -0.07
    RuntimeException
    -0.07
     tep
    -0.06
     Details
    -0.06
    strlen
    -0.06
    Jake
    -0.06
     Ker
    -0.06
     багат
    -0.06
    (cmp
    -0.06
     Scale
    -0.06
    POSITIVE LOGITS
    ）。↵
    0.07
    →
    0.06
     mapping
    0.06
    /XMLSchema
    0.06
    UID
    0.06
    ------------↵
    0.06
    umbles
    0.06
     homophobic
    0.06
     mutlu
    0.06
     tienen
    0.06
    Act Density 0.000%

    No Known Activations