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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PST
    -0.07
     modal
    -0.07
     Belfast
    -0.06
    独立
    -0.06
     Majority
    -0.06
    五月
    -0.06
     Placement
    -0.06
     nas
    -0.06
    .setLocation
    -0.06
     Likes
    -0.06
    POSITIVE LOGITS
    зу
    0.07
    FUNC
    0.07
    _tE
    0.07
     restoring
    0.07
     ")"
    0.07
    βε
    0.06
    _char
    0.06
    /usr
    0.06
    (void
    0.06
    .raises
    0.06
    Act Density 0.004%

    No Known Activations