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

    Neuronpedia

    INDEX
    Explanations

    algorithm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chiefly
    -0.07
    Ip
    -0.06
     topical
    -0.06
    ふ
    -0.06
    (vehicle
    -0.06
     layouts
    -0.06
    ("-");↵
    -0.06
    Cd
    -0.06
     PERF
    -0.06
     гем
    -0.06
    POSITIVE LOGITS
     SWITCH
    0.07
    /forms
    0.07
     intent
    0.06
     jobId
    0.06
    NJ
    0.06
     обяз
    0.06
    _Bl
    0.06
    _JOB
    0.06
    getHeight
    0.06
    IFEST
    0.06
    Act Density 0.011%

    No Known Activations