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

    Neuronpedia

    INDEX
    Explanations

    respect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bryce
    -0.07
    istrat
    -0.06
    他の
    -0.06
     collective
    -0.06
     справи
    -0.06
     Episodes
    -0.06
     trách
    -0.06
     billig
    -0.06
     cottage
    -0.06
     її
    -0.06
    POSITIVE LOGITS
     süreç
    0.07
     aspiring
    0.06
     rooftop
    0.06
    (ht
    0.06
     silicone
    0.06
    (board
    0.06
    ulpt
    0.06
    —a
    0.06
    bmp
    0.06
    こん
    0.06
    Act Density 0.001%

    No Known Activations