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

    Neuronpedia

    INDEX
    Explanations

    images and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ัพท์
    0.35
    ड़ियों
    0.34
     meaty
    0.32
    ครัว
    0.31
    ffineTransform
    0.31
     приятно
    0.31
    лово
    0.31
     పదార్థ
    0.31
    ஜ்மஹால்
    0.30
    echolog
    0.30
    POSITIVE LOGITS
    this
    0.67
    <table>
    0.65
    Wikimedia
    0.64
    This
    0.59
     Wikimedia
    0.59
     THIS
    0.55
     tämä
    0.55
    Это
    0.55
     гэта
    0.55
     this
    0.54
    Act Density 0.000%

    No Known Activations