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

    Neuronpedia

    INDEX
    Explanations

    giving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Inf
    -0.07
     Bronx
    -0.07
    करण
    -0.07
    activities
    -0.07
    roof
    -0.06
     prosper
    -0.06
    .m
    -0.06
    signed
    -0.06
    hou
    -0.06
    (Sub
    -0.06
    POSITIVE LOGITS
    (Font
    0.06
    感
    0.06
    _codec
    0.06
     minul
    0.06
     commands
    0.06
     तब
    0.06
     discontinued
    0.06
     qualité
    0.05
     irm
    0.05
    _MEDIUM
    0.05
    Act Density 0.023%

    No Known Activations