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

    Neuronpedia

    INDEX
    Explanations

    between or for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tiến
    0.43
     excision
    0.42
     như
    0.40
    )."
    0.39
    fit
    0.39
     वै
    0.39
    值
    0.39
     vai
    0.39
     UHS
    0.39
     dietary
    0.38
    POSITIVE LOGITS
     একট
    0.44
    Despatx
    0.41
     ausgesch
    0.41
    hams
    0.40
    chitz
    0.39
     სხვა
    0.39
    멕
    0.39
    **/
    0.38
     تړل
    0.38
     Mexique
    0.38
    Act Density 0.000%

    No Known Activations