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

    Neuronpedia

    INDEX
    Explanations

    sentimental words with positive or negative connotations based on personal interest

    oai_token-act-pair · gemini-2.0-flash

    addiction or intense interest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     myſelf
    -0.87
     ―――――
    -0.84
    ſelf
    -0.82
     Anſ
    -0.81
    posób
    -0.80
     Efq
    -0.80
     onCreateView
    -0.76
     Monfieur
    -0.76
    adə
    -0.76
     doubtnut
    -0.75
    POSITIVE LOGITS
    TintMode
    0.55
     “
    0.46
     transferência
    0.44
     des
    0.40
     "
    0.39
     X
    0.39
    -
    0.38
     T
    0.37
     [
    0.37
     –
    0.37
    Act Density 1.272%

    No Known Activations