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

    Neuronpedia

    INDEX
    Explanations

    URLs and documentation paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thoughts
    0.40
     rewritten
    0.38
     draws
    0.38
     compiles
    0.38
     ஆல
    0.37
     Elektrokhimiya
    0.36
     کرل
    0.36
     light
    0.36
     worth
    0.36
    silver
    0.34
    POSITIVE LOGITS
    Packages
    0.46
    ánicos
    0.45
    êng
    0.43
    ografía
    0.43
    ulich
    0.41
     स्थानिक
    0.41
     समस्याओं
    0.40
    undaria
    0.40
    multiSelectList
    0.40
    COURSE
    0.40
    Act Density 0.000%

    No Known Activations