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

    Neuronpedia

    INDEX
    Explanations

    special characters and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wilds
    0.40
     defines
    0.37
    jne
    0.36
    lions
    0.35
    となり
    0.34
     accolades
    0.34
     functors
    0.34
     antioxidants
    0.34
     insanity
    0.34
     Funeral
    0.34
    POSITIVE LOGITS
    έ
    0.43
     espan
    0.42
    respon
    0.41
     општи
    0.41
     সিনেমা
    0.41
    ربية
    0.41
    ﻱ
    0.41
     schermo
    0.40
     positivo
    0.40
    ﺑ
    0.40
    Act Density 0.000%

    No Known Activations