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

    Neuronpedia

    INDEX
    Explanations

    code execution results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     подразуме
    0.40
     способность
    0.40
     смысл
    0.40
     вопроса
    0.40
    gdock
    0.39
     Knudsen
    0.38
     вопросам
    0.38
    KN
    0.38
     Ки
    0.38
     вопро
    0.38
    POSITIVE LOGITS
     apply
    0.50
     try
    0.47
     get
    0.46
     results
    0.46
     applying
    0.46
     output
    0.45
     hasilnya
    0.45
     start
    0.43
    を行い
    0.43
     sonuc
    0.43
    Act Density 0.300%

    No Known Activations