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

    Neuronpedia

    INDEX
    Explanations

    rhetorical "you know"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    որ
    0.36
     durata
    0.36
     rằng
    0.36
    amous
    0.35
    :**
    0.35
     namelijk
    0.34
     chiaro
    0.34
     tremor
    0.33
     wyk
    0.33
    empot
    0.33
    POSITIVE LOGITS
    Meth
    0.39
    제
    0.39
    怎样
    0.38
    Pict
    0.37
     understandably
    0.36
    फल
    0.36
    MESSAGE
    0.36
     जैसी
    0.35
    ING
    0.35
     पिक्च
    0.35
    Act Density 0.002%

    No Known Activations