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

    Neuronpedia

    INDEX
    Explanations

    the word "interested", and perhaps words related to it

    oai_token-act-pair · gemini-2.0-flash

    interested

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -1.21
    #
    -0.71
    д
    -0.63
    n
    -0.63
    o
    -0.61
     there
    -0.57
     I
    -0.57
    l
    -0.56
     cade
    -0.56
     we
    -0.55
    POSITIVE LOGITS
     Efq
    0.94
    -------
    0.91
     Jefus
    0.90
     enfans
    0.88
    bibfield
    0.87
     Chrift
    0.86
     Monfieur
    0.85
     Majefty
    0.85
     ordinaires
    0.84
     religieux
    0.83
    Act Density 1.551%

    No Known Activations