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

    Neuronpedia

    INDEX
    Explanations

    programming and technical keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     වා
    0.55
     Ś
    0.46
     Conven
    0.45
     kelt
    0.43
     rapporto
    0.43
     Marine
    0.43
     дія
    0.42
     conducta
    0.42
    àu
    0.42
     godina
    0.42
    POSITIVE LOGITS
    Palm
    0.46
    acji
    0.45
    Hugh
    0.44
    oufl
    0.43
    Milwaukee
    0.41
    Long
    0.41
    טי
    0.41
    palm
    0.40
    Salt
    0.39
     lengthy
    0.39
    Act Density 0.001%

    No Known Activations