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

    Neuronpedia

    INDEX
    Explanations

    chips / snacks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ve
    0.71
    U
    0.64
    Vis
    0.62
    Nuclear
    0.59
    What
    0.57
    _
    0.57
    ING
    0.57
    Languages
    0.57
    K
    0.56
    at
    0.56
    POSITIVE LOGITS
    ем
    0.75
    ensión
    0.71
    ení
    0.69
    '।
    0.68
    ennials
    0.67
    íl
    0.67
     hurled
    0.67
    arı
    0.66
     snack
    0.66
     snacks
    0.66
    Act Density 0.021%

    No Known Activations