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

    Neuronpedia

    INDEX
    Explanations

    describing extent or usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oftentimes
    0.51
    管控
    0.48
    ഷണ
    0.45
     каждой
    0.45
    づくり
    0.44
    umuza
    0.43
    每一個
    0.43
     এটির
    0.42
    堣
    0.42
     முழுவதும்
    0.42
    POSITIVE LOGITS
     was
    0.49
     did
    0.42
     underlines
    0.40
     went
    0.40
    sset
    0.39
     advice
    0.39
     stung
    0.39
     travelled
    0.38
     suffered
    0.38
    Só
    0.38
    Act Density 0.001%

    No Known Activations