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

    Neuronpedia

    INDEX
    Explanations

    Crisis Text Line

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ších
    0.44
     siege
    0.43
     Abelian
    0.40
    siege
    0.39
     sie
    0.38
    sie
    0.38
     collapsed
    0.37
    сіння
    0.36
     sieve
    0.36
     Collagen
    0.35
    POSITIVE LOGITS
    line
    0.47
    ライン
    0.42
    eline
    0.41
    Line
    0.38
     line
    0.38
    param
    0.38
    actic
    0.37
    Hint
    0.37
     Line
    0.36
    ーリー
    0.36
    Act Density 0.018%

    No Known Activations