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

    Neuronpedia

    INDEX
    Explanations

    b

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    optimizer
    -0.08
     pady
    -0.07
     opción
    -0.07
    Paint
    -0.07
     algebra
    -0.07
     inequalities
    -0.07
    -picker
    -0.07
    paint
    -0.07
    odní
    -0.06
    lament
    -0.06
    POSITIVE LOGITS
    	hs
    0.07
     объяс
    0.07
     мой
    0.06
     selv
    0.06
    andidates
    0.06
    �
    0.06
    �
    0.06
     testify
    0.06
    霍
    0.06
    없
    0.06
    Act Density 0.001%

    No Known Activations