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

    Neuronpedia

    INDEX
    Explanations

    discord

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    shown
    -0.07
    (mx
    -0.07
     homo
    -0.06
     shown
    -0.06
    Spanish
    -0.06
    ย
    -0.06
     Potential
    -0.06
     np
    -0.06
     кноп
    -0.06
    PropertyChanged
    -0.06
    POSITIVE LOGITS
     Disc
    0.09
     discard
    0.09
    discard
    0.09
     disciples
    0.08
    Disc
    0.07
    .ext
    0.07
     discarded
    0.07
     disc
    0.07
    received
    0.07
     accept
    0.07
    Act Density 0.009%

    No Known Activations