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

    Neuronpedia

    INDEX
    Explanations

    formulas and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     வாழ்வில்
    0.44
     nostalg
    0.44
     optimality
    0.43
     smothered
    0.43
    未来
    0.42
    Methoxy
    0.42
    😞
    0.42
    㷫
    0.42
    ீரல்
    0.41
     Huyền
    0.41
    POSITIVE LOGITS
     जर
    0.42
    bd
    0.42
     jurisdiction
    0.39
    id
    0.39
    izzo
    0.38
     справо
    0.37
    ovi
    0.37
    जवळ
    0.37
     নির্ভরযোগ্য
    0.36
    f
    0.36
    Act Density 0.001%

    No Known Activations