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

    Neuronpedia

    INDEX
    Explanations

    ffmpeg commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     videa
    0.43
     زاويه
    0.42
    Вели
    0.41
    Ending
    0.40
    亻
    0.40
     という
    0.39
    ending
    0.39
    Articulation
    0.39
    angle
    0.38
     CMOS
    0.38
    POSITIVE LOGITS
     schn
    0.39
    itarian
    0.37
     sanitized
    0.37
     sanitaria
    0.37
    itag
    0.36
    淘汰
    0.36
     corrobor
    0.36
    yt
    0.36
     Embassy
    0.36
     undertaking
    0.35
    Act Density 0.015%

    No Known Activations