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

    Neuronpedia

    INDEX
    Explanations

    head-to-head comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Great
    -0.07
    震
    -0.07
    งเศส
    -0.06
    Great
    -0.06
    Simulation
    -0.06
     Blur
    -0.06
    Order
    -0.06
    .Bot
    -0.06
    synthesize
    -0.06
    -ID
    -0.06
    POSITIVE LOGITS
    RK
    0.06
     automotive
    0.06
    _hat
    0.06
     merchandise
    0.06
    celand
    0.06
     resultList
    0.06
     regulators
    0.06
     работ
    0.06
    under
    0.06
    	rd
    0.06
    Act Density 0.060%

    No Known Activations