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

    Neuronpedia

    INDEX
    Explanations

    producing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .engine
    -0.07
     Katz
    -0.07
     molt
    -0.06
     jumper
    -0.06
    /php
    -0.06
    026
    -0.06
     odp
    -0.06
    adapt
    -0.06
     Yap
    -0.06
    otts
    -0.06
    POSITIVE LOGITS
     Avust
    0.07
    最後
    0.07
     ราย
    0.07
    akedirs
    0.06
    bases
    0.06
    	logrus
    0.06
     устан
    0.06
    lies
    0.06
     переж
    0.06
    ATAL
    0.06
    Act Density 0.089%

    No Known Activations