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

    Neuronpedia

    INDEX
    Explanations

    Something or existence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rehabilitación
    0.41
     тон
    0.37
    CEPTION
    0.34
    ക്കൂ
    0.34
     quilting
    0.33
     चौक
    0.33
    óso
    0.32
     rescheduling
    0.32
    ्च
    0.32
     coaching
    0.32
    POSITIVE LOGITS
     Else
    0.49
     else
    0.46
     Anything
    0.46
    else
    0.42
     चीज
    0.41
     cosa
    0.40
     জিনিসের
    0.40
    h
    0.39
     Dev
    0.38
     EV
    0.38
    Act Density 0.010%

    No Known Activations