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

    Neuronpedia

    INDEX
    Explanations

    laughter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Timber
    -0.07
     Cin
    -0.06
    15
    -0.06
    <D
    -0.06
     weeks
    -0.06
     clocks
    -0.06
    <C
    -0.06
    _dim
    -0.06
    -logo
    -0.06
    卢
    -0.06
    POSITIVE LOGITS
     wildfires
    0.06
    (expect
    0.06
     відвід
    0.06
    (bot
    0.06
    patient
    0.06
    .subject
    0.06
    شمالی
    0.06
     ConcurrentHashMap
    0.06
    ποτε
    0.06
    ис
    0.06
    Act Density 0.008%

    No Known Activations