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

    Neuronpedia

    INDEX
    Explanations

    Beyond potential, values, credentials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    न
    0.53
     commemorates
    0.52
    ச்சி
    0.50
     complicate
    0.50
     Sachsen
    0.50
    சா
    0.49
     kingdoms
    0.49
     தருக
    0.48
    ூ
    0.48
    il
    0.47
    POSITIVE LOGITS
    ての
    0.42
    㿟
    0.42
    擞
    0.41
    tered
    0.40
    жность
    0.40
    )->
    0.39
    zA
    0.39
     selectivity
    0.39
     иллюстра
    0.39
    getItem
    0.39
    Act Density 0.000%

    No Known Activations