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

    Neuronpedia

    INDEX
    Explanations

    style and definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     voglia
    0.40
    ани
    0.38
    يدات
    0.37
    iasco
    0.36
     ускори
    0.36
    水の
    0.35
    тни
    0.35
    פות
    0.35
     Fairness
    0.35
     ratios
    0.34
    POSITIVE LOGITS
     plain
    1.41
    plain
    1.33
     Plain
    1.30
    Plain
    1.27
    definition
    1.09
     definition
    1.06
    PLAIN
    1.00
     definição
    0.98
     definitions
    0.95
     Definition
    0.95
    Act Density 0.001%

    No Known Activations