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

    Neuronpedia

    INDEX
    Explanations

    directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fl
    -0.06
     "\(
    -0.06
    /Application
    -0.06
    [train
    -0.05
     duvar
    -0.05
    osome
    -0.05
     během
    -0.05
     sıcak
    -0.05
     Coul
    -0.05
    емые
    -0.05
    POSITIVE LOGITS
    ugin
    0.08
    rimp
    0.08
     publishers
    0.08
    -of
    0.07
    νια
    0.07
    oley
    0.07
     goalt
    0.07
    Carl
    0.07
    INI
    0.07
    erty
    0.07
    Act Density 0.001%

    No Known Activations