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

    Neuronpedia

    INDEX
    Explanations

    hard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dou
    -0.06
     ultimately
    -0.06
    Shortly
    -0.06
    $output
    -0.06
    $user
    -0.06
     Opt
    -0.06
    ло
    -0.06
    produ
    -0.06
     purified
    -0.06
    -video
    -0.06
    POSITIVE LOGITS
    .validation
    0.07
    IMS
    0.07
    象
    0.07
     Decoder
    0.06
    vehicle
    0.06
     difficult
    0.06
    gpio
    0.06
     provinces
    0.06
     prise
    0.06
    GetProcAddress
    0.06
    Act Density 0.021%

    No Known Activations