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

    Neuronpedia

    INDEX
    Explanations

    electricity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fourier
    -0.08
     Dickens
    -0.06
    láv
    -0.06
     Rounds
    -0.06
     Jared
    -0.06
    ruary
    -0.06
     🙂
    -0.06
     jaký
    -0.06
     andere
    -0.06
     IEntity
    -0.06
    POSITIVE LOGITS
     also
    0.07
    vap
    0.06
     فل
    0.06
    elfast
    0.06
     operate
    0.06
     ηλεκ
    0.06
     Bulletin
    0.06
    (DIR
    0.06
    lectron
    0.06
    halt
    0.06
    Act Density 0.005%

    No Known Activations