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

    Neuronpedia

    INDEX
    Explanations

    carry over

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    texts
    0.32
    pred
    0.31
    por
    0.30
    providers
    0.29
    mosquito
    0.28
    peripheral
    0.28
    Ко
    0.28
    temper
    0.27
     vasocon
    0.27
    κε
    0.27
    POSITIVE LOGITS
     Ако
    0.33
    A
    0.31
    T
    0.29
    الي
    0.28
     %>',
    0.28
     jossa
    0.28
    Y
    0.28
     Hire
    0.27
     जोड़ा
    0.27
    R
    0.27
    Act Density 0.032%

    No Known Activations