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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Reviewed
    -0.07
     -------------------------------------------------------------------------
    -0.07
     apologized
    -0.06
    	fwrite
    -0.06
    .Quantity
    -0.06
    	HashMap
    -0.06
     Chrome
    -0.06
     appBar
    -0.06
    ]+"
    -0.06
     fwrite
    -0.06
    POSITIVE LOGITS
     pun
    0.07
    ату
    0.07
    สอบ
    0.06
    osity
    0.06
    Are
    0.06
    ritel
    0.06
    �
    0.06
    oor
    0.06
    mmo
    0.06
     ausge
    0.06
    Act Density 0.054%

    No Known Activations