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

    Neuronpedia

    INDEX
    Explanations

    country names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     `>=
    0.64
     standstill
    0.63
     prerogative
    0.59
     "[
    0.58
     конкурен
    0.57
     dexterity
    0.56
    தாகவும்
    0.54
     muzzle
    0.54
     ingrained
    0.54
    தாக
    0.54
    POSITIVE LOGITS
    ،
    0.77
    ，
    0.70
    .
    0.67
     ،
    0.66
    ၊
    0.66
    ,
    0.65
    as
    0.63
     ,
    0.61
    ؛
    0.60
     fünf
    0.55
    Act Density 0.000%

    No Known Activations