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

    Neuronpedia

    INDEX
    Explanations

    system commands, logs, and syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    烔
    0.46
     Jawa
    0.44
    Healthcare
    0.43
    睗
    0.43
    javax
    0.42
    Accessibility
    0.41
    Military
    0.40
    棲
    0.39
    ресенье
    0.39
     Accessibility
    0.38
    POSITIVE LOGITS
    nemonic
    0.46
     insidious
    0.42
     sequential
    0.40
    ologen
    0.39
     kill
    0.38
     microscope
    0.38
     architect
    0.38
     corrupt
    0.38
     picket
    0.38
     subscripts
    0.38
    Act Density 0.001%

    No Known Activations