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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    direct
    -0.08
     να
    -0.07
    .reference
    -0.07
     includes
    -0.06
    め
    -0.06
     negativity
    -0.06
    えた
    -0.06
     cutter
    -0.06
     convin
    -0.06
     containing
    -0.06
    POSITIVE LOGITS
    pherd
    0.07
     دنیا
    0.06
     треть
    0.06
    ANCH
    0.06
    čila
    0.06
     NSArray
    0.06
     srp
    0.06
    	X
    0.06
    正式
    0.06
    Washington
    0.06
    Act Density 0.000%

    No Known Activations