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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    1
    -0.57
    2
    -0.50
     
    -0.49
    Apparently
    -0.48
     apparently
    -0.48
    ‘
    -0.48
     lagi
    -0.47
     jagung
    -0.45
     likely
    -0.44
    M
    -0.44
    POSITIVE LOGITS
     pleaſure
    1.04
     photolibrary
    0.97
     itſelf
    0.91
     moschino
    0.88
     ―――――
    0.87
     myſelf
    0.86
     houſe
    0.85
     Shakspeare
    0.84
     Efq
    0.83
     iſt
    0.82
    Act Density 0.004%

    No Known Activations