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

    Neuronpedia

    INDEX
    Explanations

    technical terms or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    While
    0.86
    If
    0.72
     While
    0.70
    This
    0.70
    Unfortunately
    0.70
    <eos>
    0.67
    Then
    0.66
     Unfortunately
    0.66
    ))
    0.64
    </div>
    0.64
    POSITIVE LOGITS
     څخه
    0.89
    IDField
    0.89
     kohta
    0.87
    etrotters
    0.84
    瑁
    0.83
    などの
    0.82
     respiratoires
    0.82
     رضی
    0.81
     まで
    0.80
     さん
    0.80
    Act Density 0.254%

    No Known Activations