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

    Neuronpedia

    INDEX
    Explanations

    technical or personal context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uds
    0.45
    渟
    0.44
    unload
    0.42
     unloaded
    0.42
    ्रे
    0.41
     алып
    0.41
    uls
    0.41
    iaux
    0.41
     усилия
    0.39
     версия
    0.39
    POSITIVE LOGITS
     comments
    0.43
     concentrations
    0.42
     seeds
    0.42
     concentration
    0.40
     narrator
    0.40
     windings
    0.40
     priming
    0.39
     agron
    0.39
    Robert
    0.39
     বর্গ
    0.39
    Act Density 0.000%

    No Known Activations