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

    Neuronpedia

    INDEX
    Explanations

    them

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     baby
    -0.07
    ियल
    -0.06
     Lenovo
    -0.06
    fps
    -0.06
     Reeves
    -0.06
    _titles
    -0.06
     duct
    -0.06
    _idxs
    -0.06
     Bid
    -0.06
    init
    -0.06
    POSITIVE LOGITS
     fais
    0.07
    Will
    0.07
    .StackTrace
    0.07
     CIF
    0.07
     zorunlu
    0.07
    .ServiceModel
    0.07
     Seven
    0.06
    mesine
    0.06
     악
    0.06
    Jac
    0.06
    Act Density 0.000%

    No Known Activations