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
     رابطه
    -0.07
     dicho
    -0.07
     Tower
    -0.07
     Destination
    -0.06
     Graphic
    -0.06
    aaS
    -0.06
     Toe
    -0.06
    เศษ
    -0.06
    	Long
    -0.06
    Berry
    -0.06
    POSITIVE LOGITS
     lure
    0.06
    _constants
    0.06
     ΑΠ
    0.06
    ♥
    0.06
    _probs
    0.06
    請
    0.06
    <X
    0.06
    .ask
    0.06
     ท
    0.06
    (ep
    0.06
    Act Density 0.005%

    No Known Activations