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

    Neuronpedia

    INDEX
    Explanations

    positive sentiment related to interaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.81
    ৫
    0.80
    ার্থ
    0.74
    и
    0.73
    sa
    0.72
    Ο
    0.69
     zlo
    0.67
     পক্ষে
    0.65
    ५
    0.65
    ู
    0.64
    POSITIVE LOGITS
     roomy
    0.80
    <unused149>
    0.80
     quotients
    0.76
     Noting
    0.74
    ልቅ
    0.74
    ्यर्थ
    0.74
     deps
    0.71
    spirited
    0.71
     extrapolate
    0.71
     поговори
    0.70
    Act Density 0.186%

    No Known Activations