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

    Neuronpedia

    INDEX
    Explanations

    Now write oppositeley

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pickles
    0.30
     syndromes
    0.29
     telas
    0.28
     awk
    0.28
     lasers
    0.28
     soybeans
    0.27
     metodologia
    0.27
     dilutions
    0.27
     glum
    0.27
     difusión
    0.27
    POSITIVE LOGITS
    1
    0.29
    FundMe
    0.24
    0.23
    送料無料
    0.22
     відповід
    0.22
     जेव्हा
    0.22
    5
    0.22
    ante
    0.21
    0
    0.21
    िया
    0.21
    Act Density 0.002%

    No Known Activations