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

    Neuronpedia

    INDEX
    Explanations

    citations and scientific literature

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Flush
    0.74
    auf
    0.71
    bud
    0.69
    XL
    0.69
    刄
    0.69
     drive
    0.66
     break
    0.65
     surprise
    0.64
    resto
    0.64
     parking
    0.64
    POSITIVE LOGITS
    ؎
    1.08
    ˒
    1.00
    ⇓
    0.99
    ⁾
    0.93
     letteratura
    0.90
     Moreover
    0.90
     littérature
    0.85
    ′,
    0.80
    ,…
    0.79
    équation
    0.79
    Act Density 0.010%

    No Known Activations