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

    Neuronpedia

    INDEX
    Explanations

    old-fashioned, old-school

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    当时
    1.05
     पुढे
    0.95
    當時
    0.93
     ఇటీ
    0.92
     futura
    0.92
     lợi
    0.92
    近年来
    0.90
     atenção
    0.90
     pozdě
    0.89
    当时的
    0.88
    POSITIVE LOGITS
    fashioned
    2.35
     fashioned
    2.15
    timers
    1.67
    timer
    1.61
     timers
    1.44
    school
    1.39
    řich
    1.30
     adage
    1.29
     timer
    1.27
    enburg
    1.26
    Act Density 0.035%

    No Known Activations