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

    Neuronpedia

    INDEX
    Explanations

    code block delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ἀ
    0.47
     robberies
    0.45
    Numerous
    0.44
    NRI
    0.42
    न्देल
    0.42
    ረዳ
    0.42
    राबरी
    0.41
    «,
    0.41
    物に
    0.40
    LEMN
    0.40
    POSITIVE LOGITS
    0
    0.76
     *
    0.60
     /*
    0.57
     //
    0.53
     +
    0.52
    5
    0.51
    ,
    0.51
    x
    0.48
    .
    0.47
    *(
    0.46
    Act Density 0.267%

    No Known Activations