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

    Neuronpedia

    INDEX
    Explanations

    letters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ());↵↵
    -0.07
    117
    -0.06
     陈
    -0.06
    115
    -0.06
    &utm
    -0.06
    婆
    -0.06
    ويس
    -0.06
    ２
    -0.06
    multiline
    -0.06
    URLConnection
    -0.06
    POSITIVE LOGITS
    ually
    0.07
    (Adapter
    0.07
    /q
    0.07
    igos
    0.07
    ses
    0.07
    alement
    0.06
    -found
    0.06
     ang
    0.06
     sonunda
    0.06
     Floating
    0.06
    Act Density 0.063%

    No Known Activations