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

    Neuronpedia

    INDEX
    Explanations

    cup measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ext
    0.79
    Ext
    0.77
    Extract
    0.71
     ekst
    0.71
     EXT
    0.70
    oline
    0.69
     O
    0.67
    ext
    0.67
     Extended
    0.67
     étendue
    0.66
    POSITIVE LOGITS
    bl
    0.64
    spirator
    0.61
    plr
    0.59
    ियंस
    0.59
    Bl
    0.58
    ᑕ
    0.58
     batter
    0.57
     CPC
    0.57
    Де
    0.57
     MIM
    0.56
    Act Density 0.171%

    No Known Activations