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

    Neuronpedia

    INDEX
    Explanations

    his pocket/man; enumerate }

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ре
    0.74
    Ме
    0.65
    உ
    0.65
    approx
    0.65
    Rh
    0.64
    Sample
    0.63
     ও
    0.62
    அத
    0.61
    return
    0.61
    Địa
    0.60
    POSITIVE LOGITS
     which
    0.93
     that
    0.92
    ที่เรา
    0.89
    ที่คุณ
    0.85
     suite
    0.84
     lineup
    0.81
     module
    0.80
     development
    0.79
     framework
    0.78
     storyline
    0.77
    Act Density 0.000%

    No Known Activations