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

    Neuronpedia

    INDEX
    Explanations

    creative writing and command-line usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Intern
    0.69
     IZ
    0.68
    ታዊ
    0.67
     Matt
    0.67
    Matt
    0.65
     Holton
    0.65
     আনোয়ার
    0.65
    ையால்
    0.65
     मैट
    0.65
     Tash
    0.65
    POSITIVE LOGITS
    ブ
    0.72
     dome
    0.70
     bulbs
    0.65
    bö
    0.64
    dome
    0.63
    蕾
    0.62
    Budget
    0.62
    bg
    0.62
    บั
    0.61
    ⺆
    0.61
    Act Density 0.222%

    No Known Activations