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

    Neuronpedia

    INDEX
    Explanations

    talking about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    akkhati
    0.48
    inei
    0.46
     až
    0.42
     geist
    0.41
     sight
    0.41
     складі
    0.40
    iót
    0.40
     supernatural
    0.40
     tied
    0.40
    nosti
    0.39
    POSITIVE LOGITS
    ทาง
    0.46
    ال
    0.44
    रित
    0.42
    Nutrition
    0.41
    Easing
    0.40
     பயன்படுத்து
    0.40
     ব্যবহার
    0.39
    治疗
    0.39
     어
    0.39
    𝕥
    0.39
    Act Density 5.926%

    No Known Activations