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

    Neuronpedia

    INDEX
    Explanations

    speak

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (크기
    -0.07
    (configuration
    -0.07
    ны
    -0.06
    animation
    -0.06
    افية
    -0.06
    Row
    -0.06
     перен
    -0.06
     chce
    -0.06
     CHR
    -0.06
    งศ
    -0.05
    POSITIVE LOGITS
     speak
    0.07
     speaking
    0.07
     Talking
    0.07
    _fl
    0.07
     obed
    0.07
    Talking
    0.07
    _dark
    0.07
     Essence
    0.07
     très
    0.06
     issuing
    0.06
    Act Density 0.013%

    No Known Activations