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

    Neuronpedia

    INDEX
    Explanations

    verbal pauses & speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     menggel
    0.37
    ház
    0.37
    ຈັດ
    0.35
    🩹
    0.35
    }=[
    0.35
    гант
    0.35
    anganan
    0.35
    핌
    0.35
     charset
    0.35
    harmed
    0.34
    POSITIVE LOGITS
     verbal
    1.03
     speaking
    1.02
     utterances
    1.00
     speech
    0.99
     बोलने
    0.95
     speak
    0.94
     Speaking
    0.90
    发言
    0.89
    พูด
    0.89
     말을
    0.89
    Act Density 0.090%

    No Known Activations