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

    Neuronpedia

    INDEX
    Explanations

    text about writing songs and creative endeavors

    oai_token-act-pair · gemini-2.0-flash

    writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CYTHON
    -0.47
    推
    -0.46
     
    -0.46
     M
    -0.44
     NO
    -0.44
     ‘
    -0.44
     '
    -0.43
     R
    -0.42
     –
    -0.42
    <eos>
    -0.42
    POSITIVE LOGITS
     Efq
    0.98
     pngtree
    0.91
     myſelf
    0.91
     itſelf
    0.88
     Anſ
    0.87
     Monfieur
    0.84
     Houſe
    0.84
     Theſe
    0.83
     Shakspeare
    0.81
     Majefty
    0.80
    Act Density 1.528%

    No Known Activations