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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     roc
    -0.06
     SALE
    -0.06
    (Transform
    -0.06
    Witness
    -0.06
     zij
    -0.06
     rumors
    -0.06
    (ARG
    -0.06
     speci
    -0.06
    -sl
    -0.06
     porch
    -0.06
    POSITIVE LOGITS
     پایان
    0.07
     мил
    0.07
     spying
    0.07
    .iOS
    0.07
    ルの
    0.06
     милли
    0.06
    ائد
    0.06
    _like
    0.06
     curses
    0.06
    tracker
    0.06
    Act Density 0.000%

    No Known Activations