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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     سوق
    -0.08
     gotovo
    -0.08
    තාව
    -0.08
    usstsein
    -0.07
    ក្នុង
    -0.07
     binn
    -0.07
    තිය
    -0.07
     physique
    -0.07
     fidél
    -0.07
    _UTF
    -0.07
    POSITIVE LOGITS
     everything
    0.09
    everything
    0.08
     chords
    0.08
     Everything
    0.08
     Suppose
    0.08
     તમામ
    0.07
    paren
    0.07
     வச
    0.07
     suppose
    0.07
    _PARENT
    0.07
    Act Density 0.027%

    No Known Activations