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

    Neuronpedia

    INDEX
    Explanations

    software license disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    town
    -0.07
    fé
    -0.06
     Aging
    -0.06
     Carlton
    -0.06
    uga
    -0.06
    TURN
    -0.06
    625
    -0.06
    Reusable
    -0.06
    ária
    -0.06
     vulgar
    -0.06
    POSITIVE LOGITS
    (para
    0.07
     ύ
    0.06
     者
    0.06
    (lua
    0.06
    [jj
    0.06
     ш
    0.06
     itir
    0.06
    募
    0.06
     لع
    0.06
    (statearr
    0.06
    Act Density 0.001%

    No Known Activations