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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ger
    -0.06
     Dur
    -0.06
    _FIXED
    -0.06
     Wimbledon
    -0.06
     Pony
    -0.06
     Ran
    -0.06
     ruta
    -0.06
    Ram
    -0.06
    ウィ
    -0.05
    верд
    -0.05
    POSITIVE LOGITS
    still
    0.07
     Schema
    0.07
    plor
    0.07
    его
    0.06
     Problem
    0.06
     Moves
    0.06
    getColumn
    0.06
    SCO
    0.06
    eness
    0.06
    и
    0.06
    Act Density 0.001%

    No Known Activations