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

    Neuronpedia

    INDEX
    Explanations

    academic writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    „A
    -0.06
    pedia
    -0.06
    озі
    -0.06
     dün
    -0.05
     Luz
    -0.05
     Pearson
    -0.05
    очь
    -0.05
    [val
    -0.05
    _sum
    -0.05
    utron
    -0.05
    POSITIVE LOGITS
    (SQL
    0.07
    (formData
    0.07
     Finals
    0.07
    幻
    0.07
    USIC
    0.07
    ordinates
    0.07
    (sin
    0.07
    _hub
    0.06
     Punch
    0.06
    matcher
    0.06
    Act Density 0.057%

    No Known Activations