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

    Neuronpedia

    INDEX
    Explanations

    end

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Initial
    -0.07
    unable
    -0.07
     paths
    -0.06
     Merry
    -0.06
    hus
    -0.06
     Oscar
    -0.06
    ому
    -0.06
    know
    -0.06
    neg
    -0.06
    iface
    -0.06
    POSITIVE LOGITS
     пром
    0.07
     داشتند
    0.07
     hdr
    0.07
     stockings
    0.06
    .ma
    0.06
     소
    0.06
    ////////////////////////////////////////////////////////////////////////////////////////////////
    0.06
     mm
    0.06
    丝
    0.06
    :'',↵
    0.06
    Act Density 0.000%

    No Known Activations