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

    Neuronpedia

    INDEX
    Explanations

    describing a situation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uwen
    1.84
    Axis
    1.67
    टी
    1.63
    ри
    1.54
    idic
    1.52
     serta
    1.51
    ණය
    1.47
     mịn
    1.47
     म्हणून
    1.46
     conclusive
    1.45
    POSITIVE LOGITS
    nnnn
    2.34
    ned
    2.19
    ました
    2.16
    ز
    2.16
    nymi
    2.14
    nl
    2.11
    nent
    2.11
    du
    2.05
    de
    2.03
    th
    1.98
    Act Density 0.164%

    No Known Activations