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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nejen
    -0.07
     información
    -0.07
     jeopardy
    -0.07
    allon
    -0.07
    _EXPRESSION
    -0.07
    价
    -0.06
    -0.06
    法
    -0.06
    _attack
    -0.06
     Managers
    -0.06
    POSITIVE LOGITS
     volcan
    0.07
     giả
    0.06
     e
    0.06
     downt
    0.06
    redirectToRoute
    0.06
     الذي
    0.06
    Third
    0.06
    /*↵
    0.06
    ideshow
    0.06
    postgresql
    0.06
    Act Density 0.005%

    No Known Activations