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

    Neuronpedia

    INDEX
    Explanations

    section titles or labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     di
    0.63
     everyday
    0.60
     forced
    0.60
     daily
    0.57
     ordinary
    0.56
     od
    0.53
    iler
    0.52
    னம்
    0.52
     vast
    0.52
     tax
    0.52
    POSITIVE LOGITS
    ↵↵↵↵
    1.45
     Lastly
    1.43
    ↵↵↵↵↵
    1.41
    <end_of_turn>
    1.40
    ↵↵↵↵↵↵↵↵
    1.38
    ↵↵
    1.37
    ↵↵↵↵↵↵↵↵↵↵
    1.35
    ''.
    1.32
    ।]
    1.31
    $)$.
    1.29
    Act Density 0.162%

    No Known Activations