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

    Neuronpedia

    INDEX
    Explanations

    unit conversions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вмест
    -0.06
    ��
    -0.06
     für
    -0.06
     highways
    -0.06
    ービ
    -0.06
    (entries
    -0.06
    ocê
    -0.06
     pumping
    -0.06
    engin
    -0.06
     salads
    -0.06
    POSITIVE LOGITS
    ер
    0.07
     Krish
    0.07
    iram
    0.07
     TN
    0.07
    上海
    0.07
     이를
    0.06
     ش
    0.06
    ψε
    0.06
     Scarborough
    0.06
     HSV
    0.06
    Act Density 0.004%

    No Known Activations