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

    Neuronpedia

    INDEX
    Explanations

    return

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PET
    -0.07
     Castillo
    -0.07
    LAT
    -0.07
     pequeño
    -0.07
    YT
    -0.07
    Gt
    -0.07
    突出
    -0.07
     скры
    -0.07
    াত
    -0.07
    qrst
    -0.07
    POSITIVE LOGITS
     }↵
    0.09
     />↵↵
    0.08
     bildir
    0.08
     #-}↵↵
    0.07
     sensible
    0.07
     compromising
    0.07
     }↵↵
    0.07
     제공합니다
    0.07
     };↵↵↵
    0.07
    ;}↵↵
    0.07
    Act Density 0.005%

    No Known Activations