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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fold
    -0.07
    .ly
    -0.06
    (nil
    -0.06
    усти
    -0.06
     jelly
    -0.06
     spinner
    -0.06
    ocaust
    -0.06
     criteria
    -0.06
     evolve
    -0.06
    igh
    -0.06
    POSITIVE LOGITS
     mdb
    0.07
    .absolute
    0.06
     Chili
    0.06
     mül
    0.06
     protagon
    0.06
     рев
    0.06
    .Boolean
    0.06
    _rpc
    0.06
     Regards
    0.06
     Mull
    0.06
    Act Density 0.013%

    No Known Activations