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

    Neuronpedia

    INDEX
    Explanations

    derived consonants queues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    matching
    0.43
    mented
    0.42
     ਰਾ
    0.42
    বর্তন
    0.42
    sembling
    0.42
    themed
    0.41
    tering
    0.41
    combo
    0.41
    stopping
    0.40
    rik
    0.39
    POSITIVE LOGITS
     Derived
    0.51
    न
    0.49
    φαν
    0.47
     cons
    0.47
     ክፍ
    0.46
     vues
    0.46
     consonants
    0.46
     SalesLT
    0.46
     queues
    0.44
     viens
    0.44
    Act Density 0.002%

    No Known Activations