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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ternal
    -0.07
     fulfillment
    -0.06
     humility
    -0.06
     strr
    -0.06
    ultan
    -0.06
    	gtk
    -0.06
    Blockchain
    -0.06
     God
    -0.06
    _lambda
    -0.06
     دوم
    -0.06
    POSITIVE LOGITS
     enough
    0.07
    0.07
    -days
    0.06
     ….
    0.06
     갤
    0.06
    ez
    0.06
    fe
    0.06
    itches
    0.06
     userModel
    0.06
     priorit
    0.06
    Act Density 0.002%

    No Known Activations