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

    Neuronpedia

    INDEX
    Explanations

    halo effect and lighting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VILLE
    0.46
    EST
    0.39
    ボン
    0.38
     ¿
    0.37
     चेतावनी
    0.37
     समस्याओं
    0.36
    EMY
    0.36
    ⴹ
    0.36
    LIE
    0.35
    Periods
    0.35
    POSITIVE LOGITS
    ingu
    0.45
    istar
    0.40
     styr
    0.39
    ja
    0.38
     limiting
    0.37
    NaBr
    0.37
     guys
    0.36
    Khokhlov
    0.36
     Khan
    0.36
     raindrops
    0.36
    Act Density 0.000%

    No Known Activations