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

    Neuronpedia

    INDEX
    Explanations

    machine-generated text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    extView
    -0.08
     stop
    -0.07
     receiving
    -0.07
     ActivatedRoute
    -0.07
    Directions
    -0.07
     GridView
    -0.07
     variable
    -0.07
     другой
    -0.06
    .linspace
    -0.06
    schlü
    -0.06
    POSITIVE LOGITS
    接触
    0.07
    etto
    0.07
    -with
    0.06
    叠加
    0.06
    	F
    0.06
    粜
    0.06
     er
    0.06
    anto
    0.06
    toast
    0.06
    التزام
    0.06
    Act Density 0.107%

    No Known Activations