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

    Neuronpedia

    INDEX
    Explanations

    magic and aspiration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    煙
    0.43
    णाल
    0.42
    鞏
    0.42
    مان
    0.38
    varez
    0.38
     polar
    0.38
     Cerr
    0.38
     cherry
    0.37
    मंड
    0.37
    isserie
    0.37
    POSITIVE LOGITS
     shootings
    0.45
     shooters
    0.42
     dziś
    0.41
     шаг
    0.41
     bước
    0.38
    aks
    0.38
    Toolkit
    0.37
    across
    0.37
     bumped
    0.36
     gravely
    0.36
    Act Density 0.000%

    No Known Activations