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

    Neuronpedia

    INDEX
    Explanations

    last week

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dor
    0.43
     Verv
    0.41
     רא
    0.39
     കാണ
    0.38
     나타
    0.38
     अमिताभ
    0.38
     ह्र
    0.38
     Dor
    0.38
     confronti
    0.37
    ْب
    0.37
    POSITIVE LOGITS
    Archive
    0.41
     Archive
    0.40
     архив
    0.38
    무리
    0.38
    archive
    0.37
    GPI
    0.36
     repertoire
    0.36
    Gradient
    0.35
     Concentrate
    0.35
    娩
    0.35
    Act Density 0.009%

    No Known Activations