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

    Neuronpedia

    INDEX
    Explanations

    identity verification, validation, format

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .‏
    0.38
    ('*
    0.38
    ょ
    0.37
    リード
    0.37
    ['-
    0.36
    助于
    0.36
    ="$
    0.35
    ("$
    0.35
    モード
    0.35
    }/\
    0.35
    POSITIVE LOGITS
     reused
    0.41
     zan
    0.40
     সাড়ে
    0.40
     floats
    0.39
    绘画
    0.39
     grouped
    0.37
     usada
    0.37
     watercolor
    0.37
     ఆది
    0.37
     Clay
    0.37
    Act Density 0.000%

    No Known Activations