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

    Neuronpedia

    INDEX
    Explanations

    clear explanation or definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.45
     EDUCATION
    0.45
     önem
    0.45
     (>
    0.45
    กา
    0.44
     degrees
    0.44
     illnesses
    0.43
    \%,
    0.43
     mitra
    0.43
     болезни
    0.43
    POSITIVE LOGITS
    Clear
    1.21
     clear
    1.19
    clear
    1.09
     Clear
    1.03
     क्लियर
    1.03
    CLEAR
    0.98
    クリア
    0.95
     clearer
    0.91
    清楚
    0.91
    不清
    0.89
    Act Density 0.021%

    No Known Activations