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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     not
    -0.08
     indeed
    -0.08
    not
    -0.07
    	except
    -0.07
    .optimize
    -0.07
    новаж
    -0.07
    (default
    -0.07
    ↵
    -0.07
     NOT
    -0.07
    -start
    -0.07
    POSITIVE LOGITS
    estring
    0.06
    uí
    0.06
     trắng
    0.06
    Deserializer
    0.06
    orman
    0.06
    ,address
    0.06
    ασίας
    0.06
     DER
    0.06
    }}},↵
    0.06
    	Map
    0.06
    Act Density 0.099%

    No Known Activations