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

    Neuronpedia

    INDEX
    Explanations

    did you learn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    표
    0.48
    ਪ
    0.44
    project
    0.44
    マスク
    0.43
    writes
    0.43
    its
    0.42
    為
    0.42
    imary
    0.41
    eted
    0.41
    polynomial
    0.41
    POSITIVE LOGITS
     innych
    0.51
     conteú
    0.46
     ஒப்ப
    0.45
     Ipswich
    0.45
     χρόνο
    0.45
     pomocą
    0.45
     conoscenza
    0.44
     Avenida
    0.44
     anguish
    0.43
     início
    0.42
    Act Density 0.004%

    No Known Activations