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

    Neuronpedia

    INDEX
    Explanations

    tailor to specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ATIONAL
    0.74
    ளால்
    0.71
    褥
    0.70
    льт
    0.68
    ational
    0.67
     multipart
    0.66
    नोई
    0.66
     दर्ज
    0.65
    改装
    0.64
    MIB
    0.64
    POSITIVE LOGITS
    ored
    1.35
    oring
    1.34
    ândia
    1.17
    orm
    1.16
    wind
    1.08
    orable
    1.08
    or
    1.06
    winds
    1.05
    leur
    1.02
    ors
    1.02
    Act Density 0.021%

    No Known Activations