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

    Neuronpedia

    INDEX
    Explanations

    inflatable inflation inflate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    1.95
    т
    1.32
    ள்ளது
    1.30
    ます
    1.18
    تان
    1.17
    니다
    1.16
    t
    1.15
     ন্যায়
    1.13
    싶
    1.11
     D
    1.09
    POSITIVE LOGITS
    ic
    1.52
    ار
    1.52
    ción
    1.51
    collar
    1.44
    as
    1.40
    an
    1.36
    to
    1.36
    cactus
    1.36
    crop
    1.34
    ar
    1.34
    Act Density 0.001%

    No Known Activations