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

    Neuronpedia

    INDEX
    Explanations

    knowledge graphs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     तालुक
    0.37
    re
    0.36
    Cath
    0.36
    মোঃ
    0.36
    epik
    0.36
    iqueness
    0.35
    Colin
    0.34
    kovi
    0.33
    𝓈
    0.33
    shank
    0.33
    POSITIVE LOGITS
     knowledge
    0.82
     Knowledge
    0.73
    Knowledge
    0.68
     conoscenza
    0.65
     gained
    0.64
    产权
    0.64
     conhecimento
    0.63
    知识
    0.62
     adquirido
    0.62
    knowledge
    0.62
    Act Density 0.012%

    No Known Activations