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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Khan
    -0.08
     JM
    -0.07
    ionario
    -0.07
     indoor
    -0.07
    中国人
    -0.07
    .Google
    -0.06
    Zoom
    -0.06
     Biał
    -0.06
    سود
    -0.06
    苟
    -0.06
    POSITIVE LOGITS
    #\
    0.08
     FAC
    0.07
    textbox
    0.07
    esan
    0.07
    <<"\
    0.06
    reading
    0.06
    致辞
    0.06
    招募
    0.06
    -profit
    0.06
    exit
    0.06
    Act Density 0.008%

    No Known Activations