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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lication
    -0.25
    onder
    -0.25
    force
    -0.25
    veau
    -0.25
     <<-
    -0.24
     case
    -0.24
    lear
    -0.24
    ä¸Ģçķª
    -0.24
     acum
    -0.24
    ushi
    -0.24
    POSITIVE LOGITS
    ÑĩÑĮ
    0.28
    Ãłi
    0.26
    åĤ£
    0.26
    stdexcept
    0.25
    rô
    0.24
    ril
    0.24
    ä½İä¼°
    0.24
    /IP
    0.24
    rang
    0.24
    quila
    0.23
    Act Density 0.018%

    No Known Activations