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

    Neuronpedia

    INDEX
    Explanations

    Power Supply

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mias
    0.47
    בה
    0.46
    ohon
    0.46
    Wellness
    0.45
    iski
    0.45
    รียม
    0.44
    ਰੀ
    0.43
    လည်း
    0.43
    ransfer
    0.43
    𝗪
    0.43
    POSITIVE LOGITS
     Koh
    0.49
     Biel
    0.46
     Rah
    0.46
    satz
    0.46
     feathered
    0.45
     ²
    0.45
     apprentice
    0.43
     Brian
    0.43
     Comput
    0.42
     Quant
    0.42
    Act Density 0.001%

    No Known Activations