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

    Neuronpedia

    INDEX
    Explanations

    our

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Finland
    -0.08
     excl
    -0.06
     Russia
    -0.06
    尾
    -0.06
     Burma
    -0.06
    (xy
    -0.06
    /url
    -0.06
    /%
    -0.06
     Crimson
    -0.06
    max
    -0.06
    POSITIVE LOGITS
     our
    0.07
     اس
    0.07
     datatype
    0.06
    こんにちは
    0.06
    帶
    0.06
     Ihrem
    0.06
    bsp
    0.06
    ,,
    0.06
     editorial
    0.06
     JSName
    0.06
    Act Density 0.023%

    No Known Activations