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

    Neuronpedia

    INDEX
    Explanations

    straying from something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     classique
    -0.08
    ivir
    -0.07
     travels
    -0.07
    써
    -0.07
     zoo
    -0.07
    -0.07
     Traveling
    -0.07
     Travels
    -0.07
    ivirus
    -0.07
    (ci
    -0.07
    POSITIVE LOGITS
    it's
    0.08
    It's
    0.08
    eking
    0.08
     it's
    0.08
     opgesteld
    0.08
    might
    0.08
    .POST
    0.07
     Hasan
    0.07
    loos
    0.07
     ير
    0.07
    Act Density 0.001%
    No Known Activations