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

    Neuronpedia

    INDEX
    Explanations

    recommends tickets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inégal
    0.57
    𝒈
    0.56
     régions
    0.55
    те
    0.54
    يت
    0.53
     bericht
    0.52
     inté
    0.52
     ನಾಲ್
    0.51
    szlig
    0.51
     thatched
    0.50
    POSITIVE LOGITS
    0.70
    /
    0.56
    toUpperCase
    0.50
     Recommended
    0.46
     recommended
    0.45
     recommends
    0.44
     Certificate
    0.41
    ,
    0.41
    -
    0.41
    ᓇ
    0.41
    Act Density 0.000%

    No Known Activations