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

    Neuronpedia

    INDEX
    Explanations

    Par

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ivelany
    -0.71
     виправивши
    -0.64
     الحره
    -0.63
     الرياضيه
    -0.63
     beginnetje
    -0.62
     unknownFields
    -0.62
    Autoritní
    -0.59
    Референце
    -0.56
     otomatig
    -0.55
    انيف
    -0.55
    POSITIVE LOGITS
    IsMutable
    0.52
    LayoutPanel
    0.47
     Voiture
    0.46
    Daisy
    0.45
     Daisy
    0.44
     male
    0.44
     SafeMath
    0.44
     BoxFit
    0.43
     TextAlign
    0.42
    gogo
    0.42
    Act Density 0.002%

    No Known Activations