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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ounces
    -0.08
    night
    -0.08
     hebben
    -0.07
    	props
    -0.07
     camp
    -0.07
    ockets
    -0.07
    :${
    -0.07
    .aw
    -0.07
    (e
    -0.06
    paragus
    -0.06
    POSITIVE LOGITS
    )",↵
    0.07
    >ID
    0.07
    Mind
    0.07
    _CRC
    0.07
     psychedelic
    0.07
    サプリ
    0.07
    _roi
    0.06
     SOC
    0.06
    现代物流
    0.06
    看清
    0.06
    Act Density 0.022%

    No Known Activations