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

    Neuronpedia

    INDEX
    Explanations

    such

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PRICE
    -0.08
     Regression
    -0.07
     cursos
    -0.07
     tph
    -0.07
    ragen
    -0.07
    oris
    -0.07
    228
    -0.07
     глу
    -0.06
    terminate
    -0.06
    arius
    -0.06
    POSITIVE LOGITS
     позволя
    0.06
     Undert
    0.06
    @include
    0.06
    Indeed
    0.06
    сторія
    0.06
     everyone
    0.06
     notifying
    0.06
    hipster
    0.06
     Bennett
    0.05
     계속
    0.05
    Act Density 0.004%

    No Known Activations