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

    Neuronpedia

    INDEX
    Explanations

    centered around

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    analisi
    0.76
    চ্চ
    0.74
     על
    0.73
    insulated
    0.72
    एनएल
    0.72
     ஆசிரிய
    0.72
     discont
    0.71
    बैंक
    0.71
    unati
    0.70
     антен
    0.70
    POSITIVE LOGITS
    Around
    0.95
     around
    0.95
     Around
    0.84
    around
    0.77
     approximately
    0.76
     towards
    0.73
     Approximately
    0.73
     вокруг
    0.71
     primarily
    0.70
     surrounding
    0.70
    Act Density 0.112%

    No Known Activations