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

    Neuronpedia

    INDEX
    Explanations

    w

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bản
    -0.07
     polož
    -0.07
    jíž
    -0.07
     respectfully
    -0.07
     atlas
    -0.07
    ('../../
    -0.07
     generals
    -0.06
    rnek
    -0.06
     recur
    -0.06
     Ý
    -0.06
    POSITIVE LOGITS
    flix
    0.06
     bloginfo
    0.06
    _DISABLED
    0.06
    wind
    0.06
    ****************************************************************************
    0.06
    ()`
    0.06
    checkpoint
    0.06
     örgüt
    0.05
     imkân
    0.05
    hort
    0.05
    Act Density 0.000%

    No Known Activations