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

    Neuronpedia

    INDEX
    Explanations

    exception

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "{$
    -0.07
     caract
    -0.07
     MCC
    -0.06
     goo
    -0.06
     resist
    -0.06
     communicates
    -0.06
     accomp
    -0.06
    糙
    -0.06
    idel
    -0.06
     arsen
    -0.06
    POSITIVE LOGITS
    dict
    0.08
    _TRY
    0.07
     tuple
    0.07
    .Lines
    0.07
     humanity
    0.07
     lẽ
    0.07
    tracker
    0.06
    max
    0.06
    _SET
    0.06
    .shutdown
    0.06
    Act Density 0.001%

    No Known Activations