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

    Neuronpedia

    INDEX
    Explanations

    gallery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     techniques
    -0.09
     photographic
    -0.07
     technique
    -0.07
     abundance
    -0.07
     polarization
    -0.07
    licting
    -0.06
    :X
    -0.06
     irony
    -0.06
     dirty
    -0.06
     billboard
    -0.06
    POSITIVE LOGITS
     ;;=
    0.06
    dns
    0.06
    gcc
    0.06
     κον
    0.06
     gcc
    0.06
     dbus
    0.06
     Nha
    0.06
     olumsuz
    0.06
    하였
    0.06
    .rec
    0.06
    Act Density 0.011%

    No Known Activations