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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    稳
    -0.27
     Took
    -0.26
     indeed
    -0.26
    åIJĦæł·
    -0.26
    ç¡®å®ŀ
    -0.25
    Sam
    -0.25
    ammers
    -0.25
    äºĨä¸Ģåı£æ°Ķ
    -0.24
    åħļå§Ķ
    -0.24
     Sam
    -0.24
    POSITIVE LOGITS
    Prototype
    0.28
     /\
    0.26
    roman
    0.26
    rible
    0.25
    LAS
    0.24
    èĮĢ
    0.23
     Annex
    0.23
    à¸Ļà¸Ńà¸ģ
    0.23
    iona
    0.23
    пÑĥÑĤ
    0.23
    Act Density 0.024%

    No Known Activations