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

    Neuronpedia

    INDEX
    Explanations

    Initials and abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Deep
    -0.06
     Stuff
    -0.06
    parents
    -0.06
     �
    -0.06
     Actor
    -0.06
    #g
    -0.06
     marathon
    -0.06
     Special
    -0.06
    _ar
    -0.06
     dominant
    -0.06
    POSITIVE LOGITS
    Pager
    0.07
     kak
    0.07
     conformity
    0.06
     commenter
    0.06
     {
↵
↵
    0.06
    گل
    0.06
     buoy
    0.06
     Hải
    0.06
     Spoj
    0.06
    tery
    0.06
    Act Density 0.048%

    No Known Activations