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

    Neuronpedia

    INDEX
    Explanations

    Lore

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Baby
    -0.07
     없다
    -0.06
     snippets
    -0.06
     Zheng
    -0.06
     hayata
    -0.06
     Laden
    -0.06
     drilled
    -0.06
     patented
    -0.06
     Secondly
    -0.06
     últimos
    -0.06
    POSITIVE LOGITS
    _TP
    0.07
     Story
    0.07
     德
    0.07
     Source
    0.06
    cery
    0.06
    .Script
    0.06
     MUSIC
    0.06
    .WRITE
    0.06
     Solver
    0.06
     MP
    0.06
    Act Density 0.002%

    No Known Activations