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

    Neuronpedia

    INDEX
    Explanations

    Asking questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    function
    0.39
    utils
    0.38
     পালন
    0.38
     spite
    0.37
     ద
    0.36
    }$.
    0.35
    ӯ
    0.35
    companion
    0.33
    令
    0.33
    andy
    0.33
    POSITIVE LOGITS
     Jardin
    0.39
     cheer
    0.38
     Cheer
    0.37
     Erica
    0.34
     Julia
    0.34
     Distillery
    0.33
     SMD
    0.33
     element
    0.33
     jard
    0.33
     rooting
    0.33
    Act Density 73.357%

    No Known Activations