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

    Neuronpedia

    INDEX
    Explanations

    award ceremony names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ims
    0.72
    IN
    0.65
     einem
    0.65
     cause
    0.64
    听
    0.61
     hi
    0.61
     fr
    0.60
     i
    0.59
     einer
    0.59
     seiner
    0.59
    POSITIVE LOGITS
    BleStatus
    0.77
    ╴
    0.67
    град
    0.66
     Awards
    0.66
    दून
    0.64
    SecurityMarks
    0.64
    궬
    0.64
    िरिक्स
    0.63
    ┝
    0.63
     carbohyd
    0.61
    Act Density 0.001%

    No Known Activations