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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     robotic
    -0.06
     Bunu
    -0.06
     Bloc
    -0.06
    رو
    -0.06
     Report
    -0.06
    share
    -0.06
     shrink
    -0.06
    Processor
    -0.06
    _CHAT
    -0.06
    oodles
    -0.06
    POSITIVE LOGITS
     artículo
    0.07
    .deploy
    0.06
     Би
    0.06
     //</
    0.06
    orgetown
    0.06
     recommending
    0.06
     typically
    0.06
     animations
    0.06
    .sal
    0.06
    edení
    0.06
    Act Density 0.016%

    No Known Activations