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

    Neuronpedia

    INDEX
    Explanations

    Players declare actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NaN
    0.46
    郯
    0.42
    ッフ
    0.40
     परवानगी
    0.40
     અનુ
    0.40
     Unauthorized
    0.40
    Unauthorized
    0.40
    窕
    0.40
     ներ
    0.39
     สิน
    0.39
    POSITIVE LOGITS
     synonymous
    0.48
     cinta
    0.44
    스의
    0.44
     carrots
    0.43
     sadde
    0.43
    ↵↵
    0.42
     aldığı
    0.42
     sette
    0.42
    apal
    0.41
     otto
    0.41
    Act Density 0.006%

    No Known Activations