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

    Neuronpedia

    INDEX
    Explanations

    generally considered

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    不仅仅
    0.87
     nejen
    0.86
     not
    0.83
     Not
    0.81
    not
    0.78
    Not
    0.76
     मजबूर
    0.76
     poor
    0.76
     Bukan
    0.75
    不止
    0.75
    POSITIVE LOGITS
     никаких
    1.46
     negligible
    1.37
    没有什么
    1.36
     aucune
    1.34
    没什么
    1.31
     nessun
    1.25
     ምንም
    1.21
     nothing
    1.20
    Generally
    1.19
    generally
    1.18
    Act Density 0.598%

    No Known Activations