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

    Neuronpedia

    INDEX
    Explanations

    technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -gun
    -0.07
    .mb
    -0.07
    lüğ
    -0.06
     highway
    -0.06
     Forbes
    -0.06
     Buying
    -0.06
     Cor
    -0.06
    Ren
    -0.06
     UIControl
    -0.06
    _RA
    -0.06
    POSITIVE LOGITS
    怒
    0.06
     aussi
    0.06
     nám
    0.06
     disorders
    0.06
    震
    0.06
     Vote
    0.06
    жно
    0.06
     isinstance
    0.06
     земель
    0.06
     *=
    0.06
    Act Density 0.225%

    No Known Activations