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

    Neuronpedia

    INDEX
    Explanations

    sim

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _BUS
    -0.06
     PCs
    -0.06
     vượt
    -0.06
     adet
    -0.06
     majet
    -0.06
    	children
    -0.06
    	org
    -0.06
     rencont
    -0.06
     policemen
    -0.06
    ाभ
    -0.06
    POSITIVE LOGITS
     custom
    0.08
    sim
    0.08
     Tour
    0.07
    -orders
    0.07
     heavily
    0.07
     IM
    0.07
    ourmet
    0.07
     Mim
    0.07
     experience
    0.07
    -person
    0.06
    Act Density 0.001%

    No Known Activations