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

    Neuronpedia

    INDEX
    Explanations

    rich salts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RAM
    0.41
     press
    0.40
    osine
    0.40
    URY
    0.40
    rakes
    0.39
     presses
    0.39
    FX
    0.38
    urricular
    0.38
     равномер
    0.38
     creep
    0.38
    POSITIVE LOGITS
    asmussen
    0.42
     হিন্দ
    0.41
    InSection
    0.37
    LOUISE
    0.36
    麪
    0.36
     sabía
    0.36
     cómodo
    0.36
     ثالث
    0.35
     মিসেস
    0.35
     خودم
    0.35
    Act Density 0.000%

    No Known Activations