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

    Neuronpedia

    INDEX
    Explanations

    explanations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -library
    -0.08
     hyö
    -0.08
    date
    -0.08
     అనే
    -0.07
     вещ
    -0.07
    ‌క
    -0.07
     examination
    -0.07
    ();↵↵//
    -0.07
     ప్రకట
    -0.07
    ‌డ
    -0.07
    POSITIVE LOGITS
     motivated
    0.09
    0.08
     motivate
    0.08
     motivates
    0.08
     കാരണം
    0.08
    trat
    0.08
     أسباب
    0.07
    导致
    0.07
    Driven
    0.07
     cấu
    0.07
    Act Density 0.068%
    No Known Activations