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

    Neuronpedia

    INDEX
    Explanations

    goals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    یان
    -0.07
    AB
    -0.07
     Abr
    -0.06
     explanatory
    -0.06
     sophistication
    -0.06
     hardware
    -0.06
     LAB
    -0.06
    建设
    -0.06
    owania
    -0.06
     шт
    -0.06
    POSITIVE LOGITS
    /loose
    0.07
     कट
    0.06
     tieten
    0.06
     ResourceBundle
    0.06
    Framework
    0.06
     cling
    0.06
     {?>↵
    0.06
    арч
    0.06
     ऋ
    0.06
    .peer
    0.06
    Act Density 0.002%

    No Known Activations