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

    Neuronpedia

    INDEX
    Explanations

    challenge and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     toep
    0.60
     televisi
    0.59
    ский
    0.59
    や
    0.59
    راس
    0.56
    یر
    0.56
    شش
    0.55
     pháp
    0.54
     lintas
    0.52
     määr
    0.52
    POSITIVE LOGITS
     Foreground
    0.48
     Convenience
    0.48
    git
    0.47
    endom
    0.47
    Statement
    0.46
    den
    0.45
    gium
    0.45
    cpu
    0.45
    <<<<
    0.45
     Libertad
    0.45
    Act Density 0.000%

    No Known Activations