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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     QU
    0.82
     DIR
    0.80
    ITAR
    0.77
     TOP
    0.74
     Mille
    0.74
     Eighth
    0.74
     operating
    0.73
     dama
    0.73
     SAT
    0.73
     GIRL
    0.71
    POSITIVE LOGITS
    zero
    0.66
     am
    0.64
     psic
    0.63
     Ende
    0.63
    ంటు
    0.61
    Wein
    0.61
    bin
    0.59
    ęd
    0.59
    retry
    0.59
    찝
    0.59
    Act Density 0.004%

    No Known Activations