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

    Neuronpedia

    INDEX
    Explanations

    limited availability or rarity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uous
    1.05
    nor
    0.99
    al
    0.95
    তা
    0.92
    ication
    0.89
     பா
    0.88
     combining
    0.86
    alena
    0.85
    প
    0.85
    oug
    0.85
    POSITIVE LOGITS
     $(<
    1.34
     exceptions
    1.18
     surprises
    1.03
    toFixed
    1.02
     respite
    0.96
     voire
    0.96
    정보
    0.95
     reversible
    0.94
     aback
    0.94
     informacija
    0.93
    Act Density 0.067%

    No Known Activations