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

    Neuronpedia

    INDEX
    Explanations

    superlatives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (lon
    -0.07
    ρηση
    -0.07
     trot
    -0.07
    (machine
    -0.07
     anunci
    -0.07
    hões
    -0.06
     battalion
    -0.06
     ************************************************
    -0.06
     Hidden
    -0.06
    .turn
    -0.06
    POSITIVE LOGITS
    	context
    0.07
    ΟΚ
    0.07
    στό
    0.06
    гра
    0.06
    책
    0.06
    UIImagePickerController
    0.06
    تیجه
    0.06
     mucho
    0.06
    _site
    0.06
    SCII
    0.06
    Act Density 0.034%

    No Known Activations