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

    Neuronpedia

    INDEX
    Explanations

    structured data delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ，
    0.46
    、
    0.44
    ၊
    0.42
    ،
    0.41
    ：
    0.41
    ’
    0.39
    ґ
    0.38
    的
    0.38
    의
    0.38
    가
    0.37
    POSITIVE LOGITS
    ല്ലാം
    0.42
    aiser
    0.41
    귿
    0.41
     rapping
    0.40
     أنه
    0.39
    ertid
    0.38
     syndromes
    0.38
    люс
    0.38
    ictured
    0.38
     postponing
    0.38
    Act Density 0.001%

    No Known Activations