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

    Neuronpedia

    INDEX
    Explanations

    `.then(response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝟏
    1.09
    ның
    1.07
    𝓻
    1.04
    ﻦ
    1.02
     eſ
    0.96
    𝔯
    0.95
     impeding
    0.94
     natoque
    0.93
    은
    0.92
    이라고
    0.91
    POSITIVE LOGITS
    ą
    1.34
    í
    1.23
    ü
    1.14
    ak
    1.09
    க
    1.00
    يد
    0.98
    સ
    0.98
    ëlle
    0.97
    Fs
    0.93
    ene
    0.92
    Act Density 0.007%

    No Known Activations