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

    Neuronpedia

    INDEX
    Explanations

    Scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Roger
    -0.06
    ularity
    -0.06
    .ctrl
    -0.06
    evice
    -0.06
    Sweet
    -0.06
    Tweet
    -0.06
     notation
    -0.06
    ा�
    -0.06
    Hall
    -0.06
    'order
    -0.06
    POSITIVE LOGITS
    lift
    0.07
     Spe
    0.07
     ac
    0.07
     فراو
    0.06
    DUCT
    0.06
    ős
    0.06
     referrals
    0.06
     FIND
    0.06
    DRAW
    0.06
     wf
    0.06
    Act Density 0.015%

    No Known Activations