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

    Neuronpedia

    INDEX
    Explanations

    html tags and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.53
     declines
    0.43
     worsening
    0.41
     rift
    0.40
     vicious
    0.38
     multiplicity
    0.38
     problemen
    0.38
     fallacy
    0.38
     clash
    0.37
     heartbreak
    0.37
    POSITIVE LOGITS
    to
    0.43
    ={()
    0.42
     μαγγ
    0.41
    AsUpIndicator
    0.40
     sẽ
    0.40
     প্রত্যেক
    0.40
    Provider
    0.39
    corrh
    0.39
    เพื่อให้
    0.39
    dois
    0.39
    Act Density 0.000%

    No Known Activations