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

    Neuronpedia

    INDEX
    Explanations

    asking how to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     پوکر
    0.44
     मोर्चा
    0.44
    𒂠
    0.41
     espectacular
    0.40
     باہنی
    0.40
     Yhat
    0.40
     puisi
    0.39
     SCGS
    0.39
     ബാറ്ററി
    0.38
     pizarra
    0.38
    POSITIVE LOGITS
    st
    0.44
    p
    0.44
    I
    0.41
    z
    0.41
    K
    0.40
    -
    0.40
    E
    0.40
    P
    0.40
    ch
    0.39
    in
    0.39
    Act Density 23.516%

    No Known Activations