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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'A
    -0.08
    _DOM
    -0.07
    Env
    -0.07
     Sid
    -0.06
    pawn
    -0.06
    sembled
    -0.06
    Sid
    -0.06
    ifacts
    -0.06
    імі
    -0.06
    縮
    -0.06
    POSITIVE LOGITS
     unreliable
    0.07
    aster
    0.07
    NON
    0.07
    .ParseException
    0.06
     trận
    0.06
     зада
    0.06
     undecided
    0.06
     inter
    0.06
     pagan
    0.06
    РСР
    0.06
    Act Density 0.000%

    No Known Activations