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

    Neuronpedia

    INDEX
    Explanations

    baseball and cricket terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    是
    -1.08
     ；
    -1.03
        
    -1.02
    其他
    -1.00
    要
    -1.00
    A
    -0.99
    U
    -0.96
    第一
    -0.95
     tempe
    -0.95
     caratteristiche
    -0.94
    POSITIVE LOGITS
    eacute
    1.13
     Pues
    1.13
    Abbiamo
    1.13
    Comunic
    1.11
    Allora
    1.08
    Perché
    1.07
    تفسير
    1.06
    Mereka
    1.05
    ztes
    1.05
    枭
    1.04
    Act Density 0.003%

    No Known Activations