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

    Neuronpedia

    INDEX
    Explanations

    simple

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     facing
    -0.07
     человека
    -0.07
    気
    -0.07
     capsules
    -0.07
     nabízí
    -0.06
    Sensor
    -0.06
    啦
    -0.06
     deine
    -0.06
     bourbon
    -0.06
    stations
    -0.06
    POSITIVE LOGITS
     موسیقی
    0.07
     Baghdad
    0.07
    .oper
    0.07
    (API
    0.06
     Stanley
    0.06
     Theodore
    0.06
    .il
    0.06
     jc
    0.06
     ALOG
    0.06
    _URI
    0.06
    Act Density 0.021%

    No Known Activations