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

    Neuronpedia

    INDEX
    Explanations

    Is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hom
    -0.07
     sistem
    -0.07
    voy
    -0.06
    IFT
    -0.06
     Observable
    -0.06
     Nav
    -0.06
     инструмент
    -0.06
    snap
    -0.06
    遍
    -0.06
     High
    -0.06
    POSITIVE LOGITS
     getP
    0.07
    _VOLT
    0.07
     vita
    0.06
     olarak
    0.06
     zby
    0.06
     groom
    0.06
    ORIZATION
    0.06
    言って
    0.06
    /'.$
    0.06
     simplest
    0.06
    Act Density 0.037%

    No Known Activations