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

    Neuronpedia

    INDEX
    Explanations

    On

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rever
    -0.08
    배
    -0.07
    λά
    -0.07
     Fort
    -0.07
    det
    -0.07
     E
    -0.07
    figure
    -0.07
    Ver
    -0.07
     Gret
    -0.07
     five
    -0.06
    POSITIVE LOGITS
     On
    0.13
    On
    0.11
     ON
    0.10
     on
    0.10
    on
    0.09
    -On
    0.09
    ON
    0.08
    _On
    0.08
    ’on
    0.08
    "On
    0.08
    Act Density 0.022%

    No Known Activations