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

    Neuronpedia

    INDEX
    Explanations

    real-world classrooms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Print
    0.72
     மறை
    0.69
    らを
    0.69
    ລ
    0.68
    SMALL
    0.67
    Ready
    0.67
     ہمیشہ
    0.67
     aşağı
    0.67
     abund
    0.67
    ajada
    0.66
    POSITIVE LOGITS
     classroom
    0.89
     퇴
    0.80
    classroom
    0.74
     landet
    0.73
     classrooms
    0.71
     envy
    0.70
     lume
    0.70
     전투
    0.70
     instructional
    0.68
     관
    0.68
    Act Density 0.001%

    No Known Activations