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

    Neuronpedia

    INDEX
    Explanations

    pow / pov prefixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gastos
    0.93
    яс
    0.80
    ைகோ
    0.77
    <unused45>
    0.76
     esclare
    0.76
    katore
    0.75
    rives
    0.75
    CAL
    0.74
     sideWeight
    0.74
     എത്തി
    0.73
    POSITIVE LOGITS
     sett
    0.76
    umbr
    0.76
    um
    0.75
    ir
    0.75
     voluntary
    0.75
    mard
    0.74
     Richmond
    0.73
    more
    0.72
    un
    0.71
    ory
    0.70
    Act Density 0.004%

    No Known Activations