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

    Neuronpedia

    INDEX
    Explanations

    ExpressVPN, NordVPN, Surfshark

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sentencing
    0.61
     oncoming
    0.60
     paralysis
    0.59
     precisamente
    0.58
     humbly
    0.58
     APPEND
    0.57
     retraining
    0.56
     estan
    0.56
    irrahim
    0.55
     dosimetry
    0.55
    POSITIVE LOGITS
    რი
    0.63
    t
    0.55
    ق
    0.54
    多様
    0.54
    nen
    0.53
    ती
    0.53
    गिन
    0.50
    ps
    0.49
    ol
    0.48
    Ма
    0.48
    Act Density 0.001%

    No Known Activations