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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    consistent
    -0.07
    TRANSFER
    -0.07
     Idea
    -0.07
     survivors
    -0.07
     semi
    -0.07
     correspondent
    -0.06
     Geographic
    -0.06
     standardized
    -0.06
     definition
    -0.06
     vacations
    -0.06
    POSITIVE LOGITS
    Rachel
    0.06
     아직
    0.06
     pojist
    0.06
    xf
    0.06
     balık
    0.06
     розрах
    0.05
     plá
    0.05
     은
    0.05
     нагруз
    0.05
    uluk
    0.05
    Act Density 0.008%

    No Known Activations