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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ernest
    -0.06
     machine
    -0.06
     температуры
    -0.06
    GF
    -0.06
    ci
    -0.06
     forests
    -0.06
    Die
    -0.06
    ين
    -0.06
     reconnaissance
    -0.06
     чего
    -0.06
    POSITIVE LOGITS
    .collection
    0.07
    -facebook
    0.07
    "profile
    0.07
    textInput
    0.07
     المغرب
    0.07
     quelques
    0.07
    asia
    0.06
    _wifi
    0.06
    _PACKET
    0.06
    .Core
    0.06
    Act Density 0.120%

    No Known Activations