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

    Neuronpedia

    INDEX
    Explanations

    under tables and people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     оказался
    0.43
     Fort
    0.42
     vẫn
    0.40
     ENEM
    0.40
    WD
    0.40
     also
    0.40
    ส
    0.40
    3
    0.40
    仍然
    0.39
    のと
    0.39
    POSITIVE LOGITS
    thesis
    0.49
     শিক্ষার্থীর
    0.44
     macchina
    0.43
     differentiable
    0.42
     ছাত্রদের
    0.42
     untersucht
    0.42
    괵
    0.42
    lacht
    0.40
    考生
    0.40
    demo
    0.40
    Act Density 0.002%

    No Known Activations