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

    Neuronpedia

    INDEX
    Explanations

    plus or minus

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GetY
    -0.07
    데이트
    -0.07
    authorized
    -0.06
     udál
    -0.06
    _CONTINUE
    -0.06
    	mv
    -0.06
     Private
    -0.06
    рахов
    -0.06
    ivot
    -0.06
    เลข
    -0.06
    POSITIVE LOGITS
    .Filters
    0.07
    増
    0.07
    ुध
    0.07
     recycled
    0.06
     flattened
    0.06
    .ex
    0.06
     Id
    0.06
     added
    0.06
     баг
    0.06
    Chunk
    0.06
    Act Density 0.063%

    No Known Activations