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

    Neuronpedia

    INDEX
    Explanations

    ap

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     recent
    -0.07
     MONEY
    -0.06
    Compet
    -0.06
     POT
    -0.06
    Amb
    -0.06
     exceptional
    -0.06
     Metals
    -0.06
    -interest
    -0.06
    62
    -0.06
    iran
    -0.06
    POSITIVE LOGITS
     plunged
    0.07
    privacy
    0.07
    튼
    0.07
     impl
    0.07
    ...
↵
    0.07
    _undo
    0.07
     odor
    0.06
    (canvas
    0.06
    _YELLOW
    0.06
     scl
    0.06
    Act Density 0.067%

    No Known Activations