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

    Neuronpedia

    INDEX
    Explanations

    apps

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     util
    -0.07
    itsu
    -0.07
    utorial
    -0.07
    _eval
    -0.07
    selling
    -0.06
     Foundations
    -0.06
    (opcode
    -0.06
     suitability
    -0.06
     учеб
    -0.06
    medium
    -0.06
    POSITIVE LOGITS
     [])
    0.07
    产妇
    0.07
    夹
    0.07
    袄
    0.07
    عراض
    0.07
    とか
    0.07
    (";
    0.07
    忌
    0.07
     ».
    0.06
    (Max
    0.06
    Act Density 0.001%

    No Known Activations