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

    Neuronpedia

    INDEX
    Explanations

    matrix, transformation, structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     समझाने
    0.39
    uba
    0.37
     distracting
    0.37
    덜
    0.36
     വള
    0.35
    hem
    0.35
    astava
    0.35
    ಹೆ
    0.35
     endothelial
    0.34
     aktiv
    0.34
    POSITIVE LOGITS
    пит
    0.45
     ат
    0.44
     it
    0.43
     gt
    0.43
     itin
    0.43
     جم
    0.42
     jams
    0.42
     lit
    0.41
    ⱪ
    0.41
     ит
    0.40
    Act Density 0.000%

    No Known Activations