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

    Neuronpedia

    INDEX
    Explanations

    ot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anut
    -0.08
     tavern
    -0.07
    Ⰲ
    -0.07
    .Byte
    -0.07
    ancell
    -0.07
     פעולה
    -0.07
    亸
    -0.06
    ,SIGNAL
    -0.06
     dru
    -0.06
    .navigate
    -0.06
    POSITIVE LOGITS
     Opening
    0.08
     replacement
    0.07
    мон
    0.07
     THROUGH
    0.07
    尽快
    0.07
    概括
    0.07
    acity
    0.07
    ила
    0.07
    =True
    0.06
    amientos
    0.06
    Act Density 0.002%

    No Known Activations