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

    Neuronpedia

    INDEX
    Explanations

    first person usages of the verb "to be"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    öt
    -0.07
    unger
    -0.07
     ecstatic
    -0.06
    /tests
    -0.06
    км
    -0.06
    Flush
    -0.06
    iland
    -0.06
    æĬķ注
    -0.06
    dden
    -0.06
    âĶIJ
    -0.06
    POSITIVE LOGITS
     partial
    0.11
     fond
    0.10
     fans
    0.09
     Partial
    0.09
     sensitive
    0.09
    Partial
    0.08
    .partial
    0.08
     selective
    0.08
    partial
    0.08
    -sensitive
    0.07
    Act Density 0.023%

    No Known Activations