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
     будів
    -0.06
     mange
    -0.06
    idenav
    -0.06
     ank
    -0.06
     wand
    -0.06
    <a
    -0.06
     Regarding
    -0.06
    {};↵
    -0.06
    Und
    -0.06
     pane
    -0.06
    POSITIVE LOGITS
    Collections
    0.07
    Dashboard
    0.07
    ν
    0.07
    оки
    0.06
     shrugged
    0.06
     thỏa
    0.06
     출
    0.06
    (con
    0.06
    ोफ
    0.06
    oteric
    0.06
    Act Density 0.000%

    No Known Activations