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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fall
    -0.07
    _event
    -0.07
     destin
    -0.06
    .**************↵
    -0.06
    ")]
↵
    -0.06
    工具
    -0.06
     اند
    -0.06
     enfants
    -0.06
    .Repository
    -0.06
     JSGlobal
    -0.06
    POSITIVE LOGITS
    como
    0.07
    prot
    0.06
     OC
    0.06
     Độ
    0.06
     dễ
    0.06
     demonstrate
    0.06
    s
    0.06
     ignores
    0.06
    oh
    0.06
     PUBLIC
    0.06
    Act Density 0.009%

    No Known Activations