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

    Neuronpedia

    INDEX
    Explanations

    as or like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     specifiche
    0.42
     scuole
    0.41
     específico
    0.40
     strict
    0.40
     sekolah
    0.40
     curfew
    0.40
     strictest
    0.39
     specific
    0.39
     preschool
    0.39
     errado
    0.39
    POSITIVE LOGITS
     گردش
    0.38
     पुरात
    0.36
    benchmark
    0.36
     началом
    0.36
    ങ
    0.35
    packet
    0.35
     Subst
    0.35
    }.${
    0.34
    printk
    0.34
    ны
    0.34
    Act Density 0.001%

    No Known Activations