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
     Instagram
    -0.08
     배
    -0.07
    iska
    -0.07
     interven
    -0.06
     선택
    -0.06
    _var
    -0.06
     interv
    -0.06
     foes
    -0.06
    _LOOP
    -0.06
     oo
    -0.06
    POSITIVE LOGITS
    "]){↵
    0.07
    傳
    0.07
     Previously
    0.07
     strat
    0.07
    Previously
    0.06
    crast
    0.06
    illon
    0.06
     المل
    0.06
    dır
    0.06
    raj
    0.06
    Act Density 0.004%

    No Known Activations