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

    Neuronpedia

    INDEX
    Explanations

    visitor management, escorting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    indust
    0.38
     harbours
    0.38
    IVING
    0.37
    undering
    0.37
    DIRECT
    0.36
     kitt
    0.36
    rush
    0.36
     industry
    0.36
    ives
    0.36
     uproar
    0.36
    POSITIVE LOGITS
    敤
    0.45
    锆
    0.43
     наблюдения
    0.41
     کنه
    0.40
    čnosti
    0.40
    鋯
    0.39
    ரு
    0.39
    柰
    0.39
    čení
    0.38
     በሽታ
    0.38
    Act Density 0.000%

    No Known Activations