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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Active
    -0.07
     zaháj
    -0.06
    til
    -0.06
    qus
    -0.06
    SetBranch
    -0.06
    activated
    -0.06
    uously
    -0.06
    utils
    -0.06
     پیامبر
    -0.06
     bliss
    -0.06
    POSITIVE LOGITS
    declare
    0.07
     Cleaning
    0.07
     placing
    0.07
    �
    0.07
     Musik
    0.06
     byt
    0.06
     buying
    0.06
    _SUPPLY
    0.06
    (make
    0.06
     Rouge
    0.06
    Act Density 0.009%

    No Known Activations