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

    Neuronpedia

    INDEX
    Explanations

    hierarchical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dl
    -0.07
     ayant
    -0.06
    oir
    -0.06
    同意
    -0.06
     Adobe
    -0.06
    地下
    -0.06
    。他
    -0.06
    転
    -0.06
     Lives
    -0.06
     Jog
    -0.06
    POSITIVE LOGITS
     Marxism
    0.07
    "));
↵
    0.07
    ظمة
    0.06
    :')
    0.06
    ))))
    0.06
    Exists
    0.06
    held
    0.06
    esper
    0.06
     stockholm
    0.06
    .'<
    0.06
    Act Density 0.003%

    No Known Activations