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

    Neuronpedia

    INDEX
    Explanations

    Web development and language settings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TextBox
    -0.07
     biblical
    -0.07
    _wire
    -0.06
     roofs
    -0.06
    );"
    -0.06
    boBox
    -0.06
    racat
    -0.06
    _billing
    -0.06
     miners
    -0.06
    _marshall
    -0.06
    POSITIVE LOGITS
     postav
    0.07
     misdemean
    0.07
    quality
    0.07
    ARAM
    0.06
     salir
    0.06
    asyonu
    0.06
     în
    0.06
    +E
    0.06
     Treasure
    0.06
    ework
    0.06
    Act Density 0.004%

    No Known Activations