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

    Neuronpedia

    INDEX
    Explanations

    Ursa Major, Democracy, rental

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rect
    0.38
     Fine
    0.38
    allic
    0.38
    anée
    0.36
    isle
    0.36
    isal
    0.36
     stain
    0.36
     huh
    0.36
     ఇంకా
    0.36
    见过
    0.36
    POSITIVE LOGITS
    ثر
    0.43
     substitutions
    0.41
    ಸ್ಯ
    0.41
    ασ
    0.40
    痙
    0.40
    ως
    0.40
    ರದ
    0.38
    ρε
    0.38
     ஜெய
    0.38
     শিল্পের
    0.38
    Act Density 0.009%

    No Known Activations