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

    Neuronpedia

    INDEX
    Explanations

    a followed by a word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     it
    -1.94
     its
    -1.48
     there
    -1.30
     this
    -0.98
    ConfigService
    -0.97
     when
    -0.96
     zichzelf
    -0.96
     इसकी
    -0.96
    piscina
    -0.96
     betrekking
    -0.95
    POSITIVE LOGITS
     gese
    1.04
    rektor
    1.03
     البته
    1.03
     uLocal
    0.99
    的声音
    0.96
     a
    0.96
    quent
    0.94
     Âge
    0.94
    irms
    0.94
     geste
    0.94
    Act Density 0.030%

    No Known Activations