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

    Neuronpedia

    INDEX
    Explanations

    idea

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Australia
    -0.07
     کان
    -0.06
    that
    -0.06
    Recognition
    -0.06
     highlight
    -0.06
    uri
    -0.06
     endoth
    -0.06
    flt
    -0.06
     preprocessing
    -0.06
     cada
    -0.06
    POSITIVE LOGITS
     frowned
    0.07
    0.06
     предмет
    0.06
     lodash
    0.06
    ервые
    0.06
     Divider
    0.06
    0.06
    0.06
    manent
    0.06
    	ar
    0.06
    Act Density 0.268%

    No Known Activations