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

    Neuronpedia

    INDEX
    Explanations

    punctuation and resulting clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     liga
    0.38
     synthase
    0.38
     stabilizing
    0.38
     fehlt
    0.37
     definitively
    0.37
     decisively
    0.37
     dishonest
    0.37
     hypothesized
    0.37
     fabricated
    0.36
    不稳定
    0.36
    POSITIVE LOGITS
     sehingga
    0.65
     sodass
    0.64
     waardoor
    0.64
     Sehingga
    0.64
    resulting
    0.59
    使得
    0.56
     resulting
    0.56
     zodat
    0.56
     چنانچہ
    0.55
     resulted
    0.54
    Act Density 0.017%

    No Known Activations