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

    Neuronpedia

    INDEX
    Explanations

    potential for harm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    འི་
    0.50
     awaited
    0.48
     kitchen
    0.46
     women
    0.43
     desperately
    0.43
    ног
    0.43
     cor
    0.42
     contradicted
    0.42
     vehemently
    0.42
    ;
    0.42
    POSITIVE LOGITS
    Proceedings
    0.52
    切实
    0.49
     Nauchno
    0.47
    딜
    0.47
    Constraints
    0.46
    tau
    0.44
    恴
    0.44
    ्यक्रम
    0.44
    squiggle
    0.44
    fullpath
    0.43
    Act Density 0.000%

    No Known Activations