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

    Neuronpedia

    INDEX
    Explanations

    true/false outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tà
    0.73
    larını
    0.65
    ,\\
    0.63
    taro
    0.62
    тую
    0.61
    欝
    0.61
    lot
    0.59
     ।*
    0.59
    lains
    0.59
    티브
    0.59
    POSITIVE LOGITS
    ↵
    1.22
     or
    0.83
     has
    0.80
     can
    0.78
    на
    0.73
    ana
    0.71
    il
    0.66
    ad
    0.66
     true
    0.66
     false
    0.65
    Act Density 0.201%

    No Known Activations