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

    Neuronpedia

    INDEX
    Explanations

    prior liabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    moji
    0.28
    Ģ
    0.27
    m
    0.27
    jährige
    0.27
     to
    0.26
    scriptsize
    0.26
     från
    0.25
    ']*
    0.25
    त्रेयी
    0.25
    Sprites
    0.25
    POSITIVE LOGITS
    وال
    0.28
    و
    0.26
    োক
    0.25
    нома
    0.24
    ウ
    0.24
    >.
    0.24
    ד
    0.23
     sentinel
    0.23
     Published
    0.22
    िटेशन
    0.22
    Act Density 0.156%

    No Known Activations