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

    Neuronpedia

    INDEX
    Explanations

    storytelling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pand
    -0.07
    pun
    -0.07
     Pit
    -0.07
    ेबस
    -0.06
     Lun
    -0.06
     Quran
    -0.06
     Karachi
    -0.06
    Little
    -0.06
     Palo
    -0.06
     Fot
    -0.06
    POSITIVE LOGITS
     occasionally
    0.06
    러리
    0.06
    packed
    0.06
    γε
    0.06
    реж
    0.06
     Southampton
    0.06
    боратор
    0.06
    iences
    0.06
    bor
    0.06
     Hãy
    0.06
    Act Density 0.012%

    No Known Activations