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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ANGLE
    -0.07
    엔
    -0.07
     :-)
    -0.07
    :M
    -0.07
    حتاج
    -0.07
    -small
    -0.07
    斧
    -0.07
     passphrase
    -0.07
    舐
    -0.07
    enticate
    -0.07
    POSITIVE LOGITS
    )(
    0.07
     preocup
    0.07
     práctica
    0.07
     Photo
    0.07
    יחיד
    0.06
    Study
    0.06
    <UFunction
    0.06
    輸
    0.06
    Requirements
    0.06
    	exports
    0.06
    Act Density 0.015%

    No Known Activations