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

    Neuronpedia

    INDEX
    Explanations

    prose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attacks
    -0.08
     targeted
    -0.06
    elige
    -0.06
     Kul
    -0.06
    (Un
    -0.06
    وجود
    -0.06
     дополнитель
    -0.06
    .handler
    -0.06
     ell
    -0.06
    EQUAL
    -0.06
    POSITIVE LOGITS
     prose
    0.15
    .CreateTable
    0.08
    زش
    0.07
    	mesh
    0.07
     Verse
    0.07
    .Printf
    0.06
    .Flow
    0.06
     verse
    0.06
    .onDestroy
    0.06
    _PRODUCTS
    0.06
    Act Density 0.001%

    No Known Activations