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

    Neuronpedia

    INDEX
    Explanations

    summary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     утеп
    -0.07
     발생
    -0.07
     {-
    -0.06
    (rank
    -0.06
     impass
    -0.06
     상세
    -0.06
     정확
    -0.06
    .bias
    -0.06
     returnUrl
    -0.06
     erreur
    -0.06
    POSITIVE LOGITS
    ानम
    0.08
    /New
    0.06
    ertino
    0.06
     truths
    0.06
    caa
    0.06
     dise
    0.06
    ennial
    0.06
    LIGHT
    0.06
    .swt
    0.06
    esty
    0.06
    Act Density 0.003%

    No Known Activations