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

    Neuronpedia

    INDEX
    Explanations

    code snippets and documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    щиков
    0.72
          
    0.71
    idalgo
    0.69
     atque
    0.69
     acreage
    0.69
     który
    0.68
     ——
    0.68
     —
    0.68
    0.67
         
    0.66
    POSITIVE LOGITS
    tune
    0.81
    zona
    0.72
    orod
    0.71
    Ber
    0.70
     प्रोत्साहित
    0.70
    Viv
    0.69
    Idi
    0.69
    Cast
    0.69
    Pand
    0.66
    Tune
    0.66
    Act Density 0.035%

    No Known Activations