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

    Neuronpedia

    INDEX
    Explanations

    the word "unusual."

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mille
    -0.72
    elsa
    -0.63
    ela
    -0.61
     Kirke
    -0.61
    MemoryWarning
    -0.61
    ?>">
    -0.60
     amazed
    -0.59
    Free
    -0.58
    PLES
    -0.58
    uride
    -0.58
    POSITIVE LOGITS
    1.02
    TagMode
    0.99
    unusual
    0.93
     Unusual
    0.89
     inusual
    0.84
     unusual
    0.82
     ungewöhn
    0.82
    Unusual
    0.74
    endpush
    0.74
     uncommon
    0.72
    Act Density 0.014%

    No Known Activations