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

    Neuronpedia

    INDEX
    Explanations

    technical jargon explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鴦
    0.41
    Т
    0.41
    )}$-
    0.40
    冲
    0.40
     করিতাম
    0.39
    言って
    0.39
     Alternatively
    0.38
    深度
    0.38
    DeleteMapping
    0.38
     असू
    0.37
    POSITIVE LOGITS
     celebr
    0.41
    insel
    0.40
    celebr
    0.39
     businessmen
    0.39
    onga
    0.38
     extremists
    0.37
     intellectuals
    0.37
     religieux
    0.37
    enter
    0.37
     সমাজের
    0.37
    Act Density 0.000%

    No Known Activations