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

    Neuronpedia

    INDEX
    Explanations

    techniques, methods, and algorithms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    irma
    0.48
    这点
    0.41
    lysninger
    0.41
    glRasterPos
    0.40
    这份
    0.39
    )}`;
    0.39
    anyaan
    0.39
    淞
    0.39
    rawy
    0.38
    स्प
    0.38
    POSITIVE LOGITS
     techniques
    1.27
     technique
    1.13
     Techniques
    1.11
    techniques
    1.09
     técnicas
    1.08
     tecniche
    1.08
     Technique
    1.02
     implemented
    1.01
     methods
    0.98
     implement
    0.94
    Act Density 0.018%

    No Known Activations