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

    Neuronpedia

    INDEX
    Explanations

    often followed by a descriptor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    胝
    2.22
    ikti
    2.17
     udal
    2.13
     ذہن
    2.11
    chea
    2.01
     dedos
    2.01
    রাষ্ট
    1.99
     jó
    1.97
     Puro
    1.97
     Firearms
    1.95
    POSITIVE LOGITS
    y
    2.06
    rj
    2.06
    SScript
    2.03
    ت
    2.01
    nier
    1.88
    rift
    1.86
    assuming
    1.85
    ೀವ
    1.85
    web
    1.84
    n
    1.83
    Act Density 0.356%

    No Known Activations