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

    Neuronpedia

    INDEX
    Explanations

    computer knows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    était
    0.45
    χει
    0.43
     cioc
    0.42
     waveform
    0.41
     pourrait
    0.40
    ất
    0.40
     veloc
    0.40
     mondiale
    0.40
     kemampuan
    0.40
     sempurna
    0.39
    POSITIVE LOGITS
    нда
    0.46
    3
    0.43
    8
    0.43
    ﺘ
    0.41
    J
    0.41
    7
    0.39
    SAVE
    0.39
    VILLE
    0.38
    that
    0.37
    ﻲ
    0.37
    Act Density 1.281%

    No Known Activations