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

    Neuronpedia

    INDEX
    Explanations

    numbers and letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dearly
    2.25
    tls
    1.85
     doves
    1.79
     désormais
    1.77
     doux
    1.75
    dwyd
    1.66
     deletions
    1.63
     counselors
    1.63
    WithOptions
    1.63
     vows
    1.55
    POSITIVE LOGITS
    ۰
    2.52
    ০
    2.09
     Dile
    2.05
    ال
    1.96
    ל
    1.94
    parseDouble
    1.86
    و
    1.86
     melanogaster
    1.83
     Да
    1.81
     Dino
    1.81
    Act Density 0.050%

    No Known Activations