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

    Neuronpedia

    INDEX
    Explanations

    foreign sounds and words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     використовувати
    0.40
    រួម
    0.40
     AKA
    0.39
     फ़
    0.38
    tokenizer
    0.38
     ጭ
    0.38
     $('
    0.37
     ফি
    0.37
     phenotypes
    0.37
     над
    0.37
    POSITIVE LOGITS
    abella
    0.46
    ubon
    0.42
    Depart
    0.42
    alo
    0.39
    depart
    0.38
    accompanied
    0.38
    amba
    0.38
    運
    0.38
    uma
    0.38
    MA
    0.37
    Act Density 0.000%

    No Known Activations