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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    akers
    0.51
     crosses
    0.45
     negatively
    0.44
    uteurs
    0.42
     Crossing
    0.42
     crossed
    0.42
    ：
    0.41
    passes
    0.39
    mid
    0.39
     CROSS
    0.39
    POSITIVE LOGITS
     détect
    0.63
     感じ
    0.53
     analiza
    0.51
     bądź
    0.49
     检测
    0.49
     detect
    0.49
     checkFor
    0.48
     verrou
    0.48
    ל
    0.48
     apareció
    0.48
    Act Density 0.001%

    No Known Activations