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

    Neuronpedia

    INDEX
    Explanations

    background

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _previous
    -0.07
     jade
    -0.06
     password
    -0.06
    /:
    -0.06
    DEFAULT
    -0.06
    Splash
    -0.06
     obey
    -0.06
    pis
    -0.06
     Pool
    -0.06
    silver
    -0.06
    POSITIVE LOGITS
     retorn
    0.06
    0.06
     sä
    0.06
    узы
    0.06
     einer
    0.06
     hareket
    0.06
    もしれない
    0.06
     instrumentation
    0.06
    没有
    0.06
    功
    0.06
    Act Density 0.005%

    No Known Activations