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

    Neuronpedia

    INDEX
    Explanations

    instruction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Penny
    -0.07
     endwhile
    -0.07
     hayata
    -0.07
     competit
    -0.07
    Europe
    -0.06
    eye
    -0.06
     fiz
    -0.06
    世
    -0.06
    407
    -0.06
     campaigns
    -0.06
    POSITIVE LOGITS
    ậc
    0.07
     instructor
    0.07
    educ
    0.07
     Instructor
    0.07
     instruction
    0.07
    تباط
    0.07
    올
    0.06
    igest
    0.06
    ,...
    0.06
     Drawer
    0.06
    Act Density 0.009%

    No Known Activations