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

    Neuronpedia

    INDEX
    Explanations

    defined recursion schemes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ጶ
    0.49
    كي
    0.45
     nagyobb
    0.45
    )、
    0.45
    挕
    0.44
     դ
    0.44
    ល
    0.44
    闿
    0.44
    тература
    0.43
    伥
    0.43
    POSITIVE LOGITS
    ↵↵
    0.60
    ne
    0.54
    ra
    0.48
    ge
    0.48
     Kne
    0.48
     scavenger
    0.45
    en
    0.44
    ur
    0.44
     College
    0.44
    conc
    0.44
    Act Density 0.000%

    No Known Activations