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

    Neuronpedia

    INDEX
    Explanations

    jeopard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (curl
    -0.07
     Gavin
    -0.07
    acco
    -0.07
    练习
    -0.07
     caz
    -0.07
    Ash
    -0.07
    '),'
    -0.06
    ]]↵↵
    -0.06
     Too
    -0.06
    捂
    -0.06
    POSITIVE LOGITS
     jeopardy
    0.08
     jeopard
    0.07
    енко
    0.07
     elo
    0.07
     disparities
    0.07
     developments
    0.07
     trava
    0.07
    WP
    0.06
     bankruptcy
    0.06
    شا
    0.06
    Act Density 0.003%

    No Known Activations