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

    Neuronpedia

    INDEX
    Explanations

    ethically conflicted and flexible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     perj
    0.43
    袈
    0.43
     Archers
    0.40
     encamp
    0.38
    蠡
    0.38
     medir
    0.38
    基本的に
    0.38
     subsided
    0.37
     mosques
    0.37
     rained
    0.36
    POSITIVE LOGITS
     Optional
    0.41
     Tasks
    0.41
     جاه
    0.40
     truncate
    0.39
    software
    0.38
    verson
    0.38
     Ace
    0.38
    trunc
    0.37
    Optional
    0.36
    optional
    0.36
    Act Density 0.000%

    No Known Activations