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

    Neuronpedia

    INDEX
    Explanations

    fragment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     religieuses
    -0.65
     termica
    -0.65
     elettrica
    -0.64
     supérieures
    -0.63
     étroite
    -0.61
     profonde
    -0.60
     superiori
    -0.57
    spesies
    -0.57
     aisladas
    -0.57
     étrangère
    -0.57
    POSITIVE LOGITS
    <bos>
    0.55
    ']->
    0.52
    contentLoaded
    0.51
    sw
    0.51
    sure
    0.47
     Chwiliwch
    0.46
    sal
    0.46
     //$
    0.45
     blue
    0.45
    des
    0.45
    Act Density 0.025%

    No Known Activations