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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eptal
    -0.08
     wavelength
    -0.07
    andReturn
    -0.07
     worms
    -0.07
    cw
    -0.06
    _Tis
    -0.06
    antwort
    -0.06
    West
    -0.06
    (W
    -0.06
     snd
    -0.06
    POSITIVE LOGITS
    /Index
    0.07
    たい
    0.07
    了
    0.07
    ople
    0.07
    ดา
    0.06
     pleasure
    0.06
    ƒ
    0.06
     Place
    0.06
     культуры
    0.06
    sdale
    0.06
    Act Density 0.026%

    No Known Activations