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

    Neuronpedia

    INDEX
    Explanations

    specific subjects, technologies, and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ，
    0.48
    ،
    0.47
     ،
    0.45
    Largest
    0.44
    0.43
    ，「
    0.42
    ਰ
    0.41
    (
    0.40
    ﺎ
    0.38
    是對
    0.38
    POSITIVE LOGITS
    ↵
    0.89
    ის
    0.63
     will
    0.59
    ون
    0.56
    u
    0.54
    ik
    0.52
    es
    0.51
    els
    0.51
    own
    0.50
    ле
    0.50
    Act Density 4.773%

    No Known Activations