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

    Neuronpedia

    INDEX
    Explanations

    Java code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    뿍
    -0.07
    {}.
    -0.07
    __',
    -0.07
    .complete
    -0.07
    StackSize
    -0.07
    擔
    -0.07
    ﱡ
    -0.07
     ביום
    -0.06
    -token
    -0.06
    负责任
    -0.06
    POSITIVE LOGITS
    Anti
    0.07
    ﴫ
    0.07
    ipi
    0.07
    IGENCE
    0.07
    既要
    0.07
    ester
    0.07
    지는
    0.06
    faction
    0.06
    riminal
    0.06
    érie
    0.06
    Act Density 0.001%

    No Known Activations