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

    Neuronpedia

    INDEX
    Explanations

    mentions of the numbers two, three and four

    oai_token-act-pair · gemini-2.0-flash

    two, four

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     a
    -1.00
     an
    -0.81
    addPreferredGap
    -0.77
     another
    -0.69
     some
    -0.63
     they
    -0.59
     one
    -0.58
    SOUNDBITE
    -0.58
     the
    -0.53
     it
    -0.53
    POSITIVE LOGITS
     TAMBIÉN
    0.79
     myſelf
    0.74
     uſed
    0.68
     Monfieur
    0.67
     himſelf
    0.67
     themſelves
    0.66
     "#"
    0.64
     beſt
    0.63
     existence
    0.63
     chofe
    0.63
    Act Density 0.311%

    No Known Activations