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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arn
    -0.07
     دستی
    -0.06
    THOOK
    -0.06
    MMC
    -0.06
    nym
    -0.06
    arak
    -0.06
    OPY
    -0.06
    unny
    -0.06
     Buccane
    -0.06
     counting
    -0.06
    POSITIVE LOGITS
     Vietnam
    0.07
     Without
    0.07
     without
    0.07
     AF
    0.07
     Since
    0.07
     WITHOUT
    0.07
     or
    0.07
    Since
    0.07
     because
    0.06
    WITHOUT
    0.06
    Act Density 0.005%

    No Known Activations