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

    Neuronpedia

    INDEX
    Explanations

    Expectations and understanding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cratch
    -0.09
    DICT
    -0.08
    @include
    -0.08
    @mail
    -0.08
     conceivable
    -0.08
     consideradas
    -0.08
    กว่า
    -0.07
     lewe
    -0.07
    Mayor
    -0.07
     począt
    -0.07
    POSITIVE LOGITS
     وكيف
    0.11
    并
    0.10
     exactamente
    0.10
    在哪
    0.10
    ，并
    0.09
     precies
    0.09
     beforehand
    0.09
     دقیق
    0.09
    及
    0.09
     exactement
    0.09
    Act Density 0.335%

    No Known Activations