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

    Neuronpedia

    INDEX
    Explanations

    convincing/converting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    words
    -0.07
     outrage
    -0.06
     Upload
    -0.06
    arsity
    -0.06
     permits
    -0.06
    墓
    -0.06
     Roles
    -0.06
     mùi
    -0.06
    .mount
    -0.06
     select
    -0.06
    POSITIVE LOGITS
     자동차
    0.07
    NOT
    0.07
    quisition
    0.07
    �부
    0.06
    GtkWidget
    0.06
     cout
    0.06
    unik
    0.06
    ianne
    0.06
    (asset
    0.06
     antiqu
    0.06
    Act Density 0.102%

    No Known Activations