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

    Neuronpedia

    INDEX
    Explanations

    specific terms and descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     drugg
    0.40
     समायोजित
    0.40
    cro
    0.39
    klad
    0.38
    số
    0.37
    えない
    0.37
    不僅
    0.37
    くなった
    0.37
    8
    0.37
    ford
    0.36
    POSITIVE LOGITS
     Resource
    0.41
     avez
    0.40
     خواهد
    0.39
     Advocacy
    0.39
    >;</
    0.39
     yaptık
    0.39
     estará
    0.38
    यॉर्क
    0.38
     IMMEDIATE
    0.38
     yarı
    0.37
    Act Density 0.001%

    No Known Activations