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

    Neuronpedia

    INDEX
    Explanations

    Department

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    episode
    -0.07
     EXEC
    -0.07
     FileNotFoundError
    -0.06
    _rm
    -0.06
     프리
    -0.06
    ám
    -0.06
     zpráva
    -0.06
    icap
    -0.06
    .Values
    -0.06
    vrd
    -0.06
    POSITIVE LOGITS
    Facebook
    0.07
     زمینه
    0.07
    compute
    0.07
     outstanding
    0.07
     Galaxy
    0.07
    utura
    0.06
     "\",
    0.06
     '),
    0.06
     copy
    0.06
     Copyright
    0.06
    Act Density 0.000%

    No Known Activations