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

    Neuronpedia

    INDEX
    Explanations

    writing prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ئے
    1.33
    ביל
    1.15
    ⇤
    1.13
    1.07
     zosta
    1.06
    ந்து
    1.06
     requested
    1.05
     início
    1.05
    ۓ
    1.04
     शुरुआत
    1.03
    POSITIVE LOGITS
    м
    1.20
    م
    1.20
    OR
    1.17
     Результа
    1.16
     powert
    1.15
    mesh
    1.13
    터
    1.13
    ি
    1.13
    ем
    1.12
    스
    1.10
    Act Density 0.002%

    No Known Activations