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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chamber
    -0.06
     Tb
    -0.06
     bombers
    -0.06
     visc
    -0.06
     přiroz
    -0.06
     Muslim
    -0.06
    Rich
    -0.06
    &W
    -0.06
    isa
    -0.06
     Beast
    -0.06
    POSITIVE LOGITS
    .www
    0.07
     coherence
    0.06
     conflicting
    0.06
    .columnHeader
    0.06
    /popper
    0.06
     nå
    0.06
    :]:↵
    0.06
     включ
    0.06
    .setUp
    0.06
     pInfo
    0.06
    Act Density 0.071%

    No Known Activations