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

    Neuronpedia

    INDEX
    Explanations

    collapse

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Alic
    -0.07
    	BOOL
    -0.06
     menj
    -0.06
    ?}",
    -0.06
     bourgeois
    -0.06
    bx
    -0.06
    uses
    -0.06
    ivr
    -0.06
     místní
    -0.06
     Produk
    -0.06
    POSITIVE LOGITS
     науч
    0.07
     interchangeable
    0.07
     Wisdom
    0.06
     Hanson
    0.06
    -drop
    0.06
     ransom
    0.06
    uggestions
    0.06
     lore
    0.06
    .jackson
    0.06
     Volunteer
    0.06
    Act Density 0.002%

    No Known Activations