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

    Neuronpedia

    INDEX
    Explanations

    code and internet RP

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bicarbon
    0.59
    น้อย
    0.57
    Zona
    0.56
    ರೀ
    0.55
     hypnosis
    0.55
    ियोजना
    0.55
     htob
    0.55
    𝚣
    0.55
    জনের
    0.54
     Huerta
    0.54
    POSITIVE LOGITS
     спеціа
    0.63
     其中
    0.63
     special
    0.60
     विशेष
    0.60
     upon
    0.59
    स्प
    0.57
     especial
    0.57
     над
    0.57
     特別
    0.57
     over
    0.56
    Act Density 0.002%

    No Known Activations