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

    Neuronpedia

    INDEX
    Explanations

    Legal arguments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chimpan
    -0.07
    TAB
    -0.07
     IH
    -0.07
     tzv
    -0.06
    完全
    -0.06
     iid
    -0.06
     timers
    -0.06
     meng
    -0.06
     tráv
    -0.06
    _INIT
    -0.06
    POSITIVE LOGITS
    kits
    0.06
    	false
    0.06
    раль
    0.06
    .capture
    0.06
    DATED
    0.06
    lington
    0.06
    trand
    0.06
    ано
    0.06
    idar
    0.06
    ppy
    0.06
    Act Density 0.010%

    No Known Activations