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

    Neuronpedia

    INDEX
    Explanations

    names and name variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wise
    0.38
    argu
    0.38
     anga
    0.37
     determine
    0.36
     traversing
    0.36
     requirement
    0.36
     sæ
    0.36
     rearing
    0.36
    त्याने
    0.35
     performer
    0.35
    POSITIVE LOGITS
     تانيه
    0.49
    AppLink
    0.42
     अनुराग
    0.41
     Docsity
    0.41
    Mrs
    0.40
    family
    0.40
    ColorBit
    0.40
    쬐
    0.40
     स्ट
    0.40
    ophora
    0.40
    Act Density 0.008%

    No Known Activations