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

    Neuronpedia

    INDEX
    Explanations

    ordinal positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    immagine
    0.70
    hôtel
    0.64
    रिडोर
    0.64
    siehe
    0.64
    wonderful
    0.63
    ική
    0.62
    矵
    0.62
    ată
    0.61
    asă
    0.61
    ڎ
    0.61
    POSITIVE LOGITS
     or
    0.71
     (
    0.68
    ,
    0.66
    0.63
     criterion
    0.62
     granularity
    0.61
     compounds
    0.59
     layer
    0.55
     maupun
    0.55
     mechanism
    0.54
    Act Density 0.004%

    No Known Activations