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

    Neuronpedia

    INDEX
    Explanations

    storage of data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    etic
    0.41
    Fil
    0.40
    isChecked
    0.40
     Producers
    0.39
    apse
    0.39
    Arn
    0.38
     Wesleyan
    0.38
    entz
    0.38
    presumably
    0.38
     Truth
    0.38
    POSITIVE LOGITS
     λειτουργ
    0.46
    代引不可
    0.46
    話題
    0.44
     sentimos
    0.44
     विघ
    0.44
     =-\
    0.44
     mañana
    0.43
     Mai
    0.43
     ఎక్కువ
    0.43
     funcionando
    0.43
    Act Density 0.009%

    No Known Activations