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

    Neuronpedia

    INDEX
    Explanations

    French names/locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     console
    -0.06
     Amir
    -0.06
     diminishing
    -0.06
     cultura
    -0.06
     grant
    -0.06
     defining
    -0.06
     Irene
    -0.06
     asks
    -0.06
    ow
    -0.06
     caracter
    -0.06
    POSITIVE LOGITS
     д
    0.07
    Tur
    0.07
    .signal
    0.07
    .raises
    0.07
    "crypto
    0.07
    t
    0.07
    ColorBrush
    0.06
    .Space
    0.06
    ческой
    0.06
    ,unsigned
    0.06
    Act Density 0.003%

    No Known Activations