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

    Neuronpedia

    INDEX
    Explanations

    /** comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     UInt
    0.43
     typeof
    0.41
    ᒡ
    0.40
    ārt
    0.39
    ্রাজ
    0.39
    ubine
    0.38
    ؓ
    0.38
     incrementar
    0.37
    रेखा
    0.37
     NIR
    0.37
    POSITIVE LOGITS
    🔓
    0.37
    ouer
    0.34
     Philipp
    0.34
    azo
    0.34
    🍕
    0.34
    Philipp
    0.33
    spring
    0.33
     shut
    0.33
    pyrimidine
    0.33
    графі
    0.33
    Act Density 0.004%

    No Known Activations