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

    Neuronpedia

    INDEX
    Explanations

    you followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     the
    0.46
     toxins
    0.45
     verses
    0.43
     pesticide
    0.41
     strains
    0.41
     terms
    0.40
    स्ताव
    0.40
     substation
    0.39
     padding
    0.39
     toxic
    0.39
    POSITIVE LOGITS
     मुश्किल
    0.45
     wechseln
    0.45
    google
    0.44
     жизнен
    0.43
    chooser
    0.42
     ích
    0.41
    可以选择
    0.41
     হয়ত
    0.41
     حيات
    0.41
    rowser
    0.41
    Act Density 0.007%

    No Known Activations