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

    Neuronpedia

    INDEX
    Explanations

    code and technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fault
    -0.06
    rıca
    -0.06
     dwar
    -0.06
     reinc
    -0.06
     Anda
    -0.06
    ética
    -0.06
     AMA
    -0.06
     країн
    -0.06
     apis
    -0.06
     APK
    -0.06
    POSITIVE LOGITS
    util
    0.07
    浪
    0.07
    olving
    0.06
    ViewController
    0.06
    JsonValue
    0.06
    光
    0.06
    innacle
    0.06
    �
    0.06
    /opt
    0.06
     garage
    0.06
    Act Density 0.001%

    No Known Activations