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

    Neuronpedia

    INDEX
    Explanations

    "to be" verb forms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ãĥŀãĤ¤
    -0.28
    ({↵↵
    -0.25
     spit
    -0.25
     ratified
    -0.25
    ç©¿è¡£
    -0.24
    untime
    -0.24
     tabindex
    -0.23
    conversion
    -0.23
    ä¸ĬçĻ¾
    -0.23
    ullet
    -0.23
    POSITIVE LOGITS
    utes
    0.27
    yps
    0.27
    edef
    0.25
     пÑĢава
    0.25
    itionally
    0.24
     Red
    0.24
    çݯå¢ĥä¸Ń
    0.24
    æŸ
    0.24
    çݯå¢ĥä¸ĭ
    0.24
    -working
    0.24
    Act Density 0.773%

    No Known Activations