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

    Neuronpedia

    INDEX
    Explanations

    credit card offers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     calibration
    -0.07
    users
    -0.07
     flourish
    -0.07
     Server
    -0.06
     norms
    -0.06
    美國
    -0.06
     Legend
    -0.06
    .DataPropertyName
    -0.06
    bits
    -0.06
    מ
    -0.06
    POSITIVE LOGITS
     understands
    0.07
     　 　 　 　
    0.06
     Đối
    0.06
    _GP
    0.06
     jaké
    0.06
    _parent
    0.06
     sono
    0.06
     dataType
    0.06
    070
    0.06
    OfType
    0.06
    Act Density 0.018%

    No Known Activations