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

    Neuronpedia

    INDEX
    Explanations

    foundation for learning or career

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \
    0.53
     with
    0.49
    enn
    0.47
     Министерство
    0.45
    0
    0.45
    د
    0.45
    eding
    0.43
    ，
    0.43
    act
    0.43
    ent
    0.42
    POSITIVE LOGITS
    ש
    0.62
     basis
    0.57
     yere
    0.57
    も
    0.56
    ↵
    0.55
    י
    0.54
    の実
    0.52
    x
    0.52
    פ
    0.52
    כ
    0.52
    Act Density 0.006%

    No Known Activations