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

    Neuronpedia

    INDEX
    Explanations

    evolutionary theory, danger, hath not

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    preuve
    0.50
    вей
    0.48
    堰
    0.48
    ًا
    0.46
    גע
    0.45
     prover
    0.45
    логии
    0.45
    ீரல்
    0.45
     एक्सप्रेस
    0.45
     વિચ
    0.45
    POSITIVE LOGITS
     Uk
    0.48
     mand
    0.44
     uk
    0.43
     Top
    0.42
     fate
    0.41
     poles
    0.40
     ADHD
    0.40
     blog
    0.39
     ),
    0.39
     Robert
    0.39
    Act Density 0.384%

    No Known Activations