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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Adult
    -0.07
    سین
    -0.06
     rall
    -0.06
    альна
    -0.06
     engineer
    -0.06
     防
    -0.06
     licensed
    -0.06
    (Post
    -0.06
     chast
    -0.06
     NavLink
    -0.06
    POSITIVE LOGITS
     plaats
    0.08
     záp
    0.06
    noho
    0.06
     yapar
    0.06
    .ViewModel
    0.06
     words
    0.06
    сім
    0.06
     CheckBox
    0.06
    fad
    0.06
     кисл
    0.06
    Act Density 0.001%

    No Known Activations