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

    Neuronpedia

    INDEX
    Explanations

    positive sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    @a
    -0.07
    ネ
    -0.06
     assistants
    -0.06
    що
    -0.06
    figur
    -0.06
    /Layout
    -0.06
     densities
    -0.06
     weigh
    -0.06
    stav
    -0.06
    (&___
    -0.06
    POSITIVE LOGITS
     эконом
    0.07
    _trim
    0.07
     Μετα
    0.06
    _equals
    0.06
     hút
    0.06
    	Point
    0.06
     XCTest
    0.06
     Před
    0.06
     komment
    0.06
     RTE
    0.06
    Act Density 0.229%

    No Known Activations