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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Slave
    -0.07
     rằng
    -0.07
    だな
    -0.07
    „V
    -0.07
     inform
    -0.07
     that
    -0.07
    quest
    -0.06
    "In
    -0.06
     amb
    -0.06
    inces
    -0.06
    POSITIVE LOGITS
    ping
    0.07
    <any
    0.07
     £
    0.07
     六
    0.06
    是否
    0.06
     pitched
    0.06
     toJson
    0.06
    六
    0.06
     mouseX
    0.06
    celain
    0.06
    Act Density 0.008%

    No Known Activations