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

    Neuronpedia

    INDEX
    Explanations

    resources and explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    albeit
    0.72
     totiž
    0.71
    .""
    0.71
    .”
    0.71
    .“
    0.70
    ."
    0.69
    integer
    0.64
    array
    0.62
    narr
    0.61
     affixed
    0.61
    POSITIVE LOGITS
    '):
    1.18
    :}
    1.18
    :')
    1.13
    :',
    1.09
    :");
    1.07
    ?:
    1.06
    াঃ
    1.06
    </h3>
    1.05
    +:
    1.04
    }):
    1.04
    Act Density 0.226%

    No Known Activations