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

    Neuronpedia

    INDEX
    Explanations

    List

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fol
    -0.07
    .setPrototypeOf
    -0.07
    Luc
    -0.06
    .Full
    -0.06
    _eg
    -0.06
     SetUp
    -0.06
     })).
    -0.06
     sunk
    -0.06
    τικές
    -0.06
     Riv
    -0.06
    POSITIVE LOGITS
    集中
    0.07
    卡
    0.06
    baş
    0.06
     vrch
    0.06
    Transition
    0.06
    matter
    0.06
     Bradley
    0.06
    час
    0.06
    slot
    0.06
     луч
    0.06
    Act Density 0.001%

    No Known Activations