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

    Neuronpedia

    INDEX
    Explanations

    say define

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iland
    -0.08
     Environment
    -0.07
     Covenant
    -0.07
     []).
    -0.07
    [random
    -0.07
     remarkably
    -0.07
    justice
    -0.06
     {{{
    -0.06
    国防
    -0.06
     ולאחר
    -0.06
    POSITIVE LOGITS
     Journey
    0.07
    ///<
    0.07
     linger
    0.06
    庼
    0.06
    㛃
    0.06
    -digit
    0.06
    rob
    0.06
    쉿
    0.06
     floors
    0.06
    的经历
    0.06
    Act Density 0.001%

    No Known Activations