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

    Neuronpedia

    INDEX
    Explanations

    name endings and components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Auswirkungen
    0.22
     Probleme
    0.21
     Genau
    0.21
     Smartphones
    0.21
     passende
    0.21
     Satu
    0.21
     Nós
    0.21
     problemat
    0.21
     Obr
    0.21
     Epson
    0.21
    POSITIVE LOGITS
    או
    0.24
    ↵
    0.23
    কে
    0.22
    са
    0.22
    हूं
    0.21
     ನಡೆಸ
    0.21
    о
    0.21
    稱為
    0.20
    <unused1068>
    0.20
     ኩ
    0.19
    Act Density 0.097%

    No Known Activations