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

    Neuronpedia

    INDEX
    Explanations

    middle point or halfway

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    多い
    2.19
    Honestly
    2.12
    graphicx
    2.05
    bij
    1.99
    ä
    1.97
    ast
    1.95
     immediate
    1.94
    ви
    1.94
    етки
    1.91
    mettre
    1.89
    POSITIVE LOGITS
     baya
    2.58
    ﻔ
    2.33
    این
    2.26
     tačiau
    2.24
     stejně
    2.22
     Более
    2.21
     realizacji
    2.21
    런
    2.20
    वें
    2.17
     lectura
    2.17
    Act Density 0.020%

    No Known Activations