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

    Neuronpedia

    INDEX
    Explanations

    focus, invert, broader

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.69
    ↵↵
    0.68
    ,
    0.65
     (
    0.58
    :
    0.49
    Mail
    0.49
    .,
    0.48
    Deux
    0.48
    ।
    0.46
    .:
    0.45
    POSITIVE LOGITS
     garantir
    0.50
     cardí
    0.49
     discretization
    0.48
     другие
    0.46
     kontinu
    0.46
     permittivity
    0.46
    ただし
    0.45
     desviación
    0.45
    pSensor
    0.45
     alltid
    0.45
    Act Density 0.618%

    No Known Activations