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

    Neuronpedia

    INDEX
    Explanations

    Central proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ونس
    0.40
     경우는
    0.38
    霟
    0.38
    优化
    0.38
     ავ
    0.36
    લમાં
    0.36
     {*}
    0.35
    Optimization
    0.35
     Ov
    0.34
    একজন
    0.34
    POSITIVE LOGITS
    EMPL
    0.42
     Phen
    0.41
    pied
    0.40
     surve
    0.39
    Phen
    0.39
     tín
    0.39
    ia
    0.38
     embed
    0.38
     phen
    0.38
    ition
    0.38
    Act Density 0.001%

    No Known Activations