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

    Neuronpedia

    INDEX
    Explanations

    salary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .instances
    -0.07
     Musk
    -0.06
     dominant
    -0.06
    альних
    -0.06
    有效
    -0.06
    �
    -0.06
    птом
    -0.06
    _ct
    -0.06
     talks
    -0.06
     otras
    -0.06
    POSITIVE LOGITS
     Ross
    0.07
    Destination
    0.07
    Pay
    0.06
    -paid
    0.06
     territory
    0.06
     Rate
    0.06
    Ross
    0.06
     сор
    0.06
    つぶ
    0.06
    .As
    0.06
    Act Density 0.011%

    No Known Activations