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

    Neuronpedia

    INDEX
    Explanations

    ownership, beauty, capabilities, accuracy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    authorized
    1.02
    ianza
    1.02
    }-\
    0.99
    꼴
    0.98
    reth
    0.98
    homme
    0.96
     बढ़े
    0.94
     možnosti
    0.94
    ය
    0.93
    éct
    0.93
    POSITIVE LOGITS
     deutlich
    1.24
    蚀
    1.19
    मोरी
    1.15
    穌
    1.11
    ابعة
    1.11
    И
    1.10
     lid
    1.10
    𝒽
    1.10
    webElementXpaths
    1.09
    См
    1.09
    Act Density 0.001%

    No Known Activations