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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mb
    -0.07
    	ff
    -0.07
     ++)↵
    -0.06
     علمی
    -0.06
    .vendor
    -0.06
    ظة
    -0.06
    (ml
    -0.06
    화를
    -0.06
    dbl
    -0.06
    ])(
    -0.06
    POSITIVE LOGITS
     vanilla
    0.07
     různých
    0.06
    ício
    0.06
     buildings
    0.06
    Website
    0.06
    知识
    0.06
    Add
    0.06
    isse
    0.06
     också
    0.06
     kamp
    0.06
    Act Density 0.000%

    No Known Activations