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

    Neuronpedia

    INDEX
    Explanations

    online privacy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Yale
    -0.07
    無
    -0.07
     happens
    -0.07
     fairness
    -0.07
     Armstrong
    -0.07
     repeat
    -0.06
    iform
    -0.06
    Nature
    -0.06
     draggable
    -0.06
     Kapoor
    -0.06
    POSITIVE LOGITS
    410
    0.07
    EIF
    0.07
     ent
    0.07
     EVP
    0.06
     ww
    0.06
    buquerque
    0.06
    'LBL
    0.06
     ür
    0.06
     Beverage
    0.06
    _red
    0.06
    Act Density 0.044%

    No Known Activations