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

    Neuronpedia

    INDEX
    Explanations

    sets of things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    কির
    0.41
    におすすめ
    0.41
     ہمیشہ
    0.40
    uldig
    0.39
     पल
    0.39
     sıcak
    0.39
    𝔾
    0.39
     hoera
    0.38
    最短
    0.38
     모든
    0.38
    POSITIVE LOGITS
    ಚ್
    0.39
    Singer
    0.38
     anthropogenic
    0.38
     relegated
    0.37
     pamoja
    0.36
     সংস্কৃত
    0.36
    Chronic
    0.36
    TextMesh
    0.35
     grouped
    0.35
     ceramics
    0.35
    Act Density 0.003%

    No Known Activations