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

    Neuronpedia

    INDEX
    Explanations

    code/data tables

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     experimentation
    -0.06
     专
    -0.06
    (wp
    -0.06
    _pwd
    -0.06
    .Mar
    -0.06
     GRAT
    -0.06
    _PC
    -0.06
     sın
    -0.06
    DP
    -0.06
    .OP
    -0.06
    POSITIVE LOGITS
    malink
    0.07
     Offer
    0.07
    ful
    0.07
    meet
    0.06
     offer
    0.06
    gh
    0.06
    query
    0.06
     container
    0.06
     Bates
    0.06
     allele
    0.06
    Act Density 1.303%

    No Known Activations