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

    Neuronpedia

    INDEX
    Explanations

    think

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    madığı
    -0.07
     अब
    -0.06
     cares
    -0.06
     chant
    -0.06
     DSP
    -0.06
     boat
    -0.06
     lifted
    -0.06
    sız
    -0.06
    ่าเป
    -0.06
    (Code
    -0.06
    POSITIVE LOGITS
    нання
    0.06
    FORCE
    0.06
     있으며
    0.06
    emoji
    0.06
    ��
    0.06
    公路
    0.06
     escort
    0.06
     TableName
    0.06
    estate
    0.06
     rehabilitation
    0.06
    Act Density 0.004%

    No Known Activations