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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     curse
    -0.07
    opies
    -0.07
    run
    -0.07
     polishing
    -0.06
    ุณ
    -0.06
    Run
    -0.06
    PLAN
    -0.06
     run
    -0.06
    病
    -0.06
     JA
    -0.06
    POSITIVE LOGITS
    ParallelGroup
    0.07
    .WriteHeader
    0.07
    .setRequestHeader
    0.07
    _fb
    0.06
    .textContent
    0.06
    スポ
    0.06
    FAILURE
    0.06
    (status
    0.06
    (Blueprint
    0.06
     antig
    0.06
    Act Density 0.093%

    No Known Activations