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

    Neuronpedia

    INDEX
    Explanations

    Okay, thanks, greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ເພດ
    0.99
    िनेशन
    0.87
    ណ៌
    0.86
     txtbtn
    0.86
     Romantic
    0.85
    <unused2032>
    0.83
    သေး
    0.82
    ິດຕ
    0.82
    ორის
    0.81
     forêts
    0.81
    POSITIVE LOGITS
    Ah
    0.80
    For
    0.75
     effectively
    0.75
     শ্রম
    0.72
     thanks
    0.70
     occasionally
    0.68
    O
    0.68
    Un
    0.68
    記者
    0.66
    Thanks
    0.66
    Act Density 0.001%

    No Known Activations