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

    Neuronpedia

    INDEX
    Explanations

    form input and label generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Adrien
    -0.91
    恂
    -0.91
    ivity
    -0.91
     potreb
    -0.90
    Warsaw
    -0.85
     anvä
    -0.84
    setCellStyle
    -0.84
    ἔ
    -0.83
     darbu
    -0.81
    ذر
    -0.80
    POSITIVE LOGITS
    Paul
    0.93
     Hidden
    0.88
     衣服
    0.85
     있으며
    0.85
    Hidden
    0.85
     bát
    0.84
    ることができる
    0.83
     płasz
    0.82
     said
    0.81
    既然
    0.81
    Act Density 0.009%

    No Known Activations