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

    Neuronpedia

    INDEX
    Explanations

    URLs, dates, and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     वेगवेग
    0.99
    ০
    0.87
     sixteen
    0.84
    ०
    0.82
     unrivalled
    0.82
     बॉलीवुड
    0.82
    fifty
    0.81
    highest
    0.81
    ٠
    0.81
    ０
    0.80
    POSITIVE LOGITS
    Met
    0.71
    aju
    0.71
     Met
    0.70
    月
    0.67
     işlet
    0.64
     लेंगे
    0.63
    날
    0.63
    ούς
    0.62
     فول
    0.62
     Sap
    0.62
    Act Density 0.042%

    No Known Activations