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

    Neuronpedia

    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     státu
    -0.07
     acqu
    -0.07
     Assert
    -0.06
     Hardcover
    -0.06
     nebude
    -0.06
     dejting
    -0.06
    stav
    -0.06
    umph
    -0.06
    Pk
    -0.06
    ]')↵
    -0.06
    POSITIVE LOGITS
     installs
    0.06
     Ta
    0.06
     트
    0.06
    ΙΣ
    0.06
    lower
    0.06
    .List
    0.06
     functioning
    0.05
     RS
    0.05
    líž
    0.05
     Dart
    0.05
    Act Density 0.001%

    No Known Activations