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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rieve
    -0.08
     Trev
    -0.07
     Art
    -0.07
    _tr
    -0.07
     Bard
    -0.06
    _AREA
    -0.06
     سه
    -0.06
    urator
    -0.06
     pohod
    -0.06
    .Parent
    -0.06
    POSITIVE LOGITS
     cigarettes
    0.07
    ..↵
    0.07
     Computers
    0.07
    出す
    0.06
    OutOfRangeException
    0.06
    0.06
    CG
    0.06
    Changing
    0.06
    %.↵
    0.06
     wg
    0.06
    Act Density 0.011%

    No Known Activations