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

    Neuronpedia

    INDEX
    Explanations

    snippets from longer texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     divor
    -0.07
    OrUpdate
    -0.06
     Blocking
    -0.06
    ethe
    -0.06
     Narrow
    -0.06
     başlam
    -0.06
    dw
    -0.06
     blocking
    -0.06
    -sur
    -0.06
     форм
    -0.06
    POSITIVE LOGITS
    essa
    0.07
    unt
    0.06
     -↵↵
    0.06
     sơ
    0.06
    =”
    0.06
    /")
    0.06
    аблиц
    0.06
     coalition
    0.06
    TextLabel
    0.06
    플
    0.06
    Act Density 0.328%

    No Known Activations