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

    Neuronpedia

    INDEX
    Explanations

    numbers and specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     collaborations
    0.56
    bserv
    0.55
     collaboration
    0.54
     enthusiasm
    0.54
     tunnels
    0.53
     Ў
    0.52
    consin
    0.52
     modular
    0.52
    hrm
    0.52
     occupants
    0.51
    POSITIVE LOGITS
    ก
    0.57
    ב
    0.55
    ών
    0.50
    له
    0.49
    يل
    0.47
    ের
    0.46
    ים
    0.46
     moitié
    0.46
    ی
    0.45
    ซ์
    0.45
    Act Density 0.000%

    No Known Activations