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

    Neuronpedia

    INDEX
    Explanations

    service charge

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Capital
    0.43
     Legislative
    0.41
     Longitudinal
    0.40
     provide
    0.39
     ,
    0.38
     has
    0.37
     Future
    0.37
     Money
    0.36
     Ge
    0.36
     lobby
    0.36
    POSITIVE LOGITS
     CLIENTI
    0.44
     namani
    0.42
     вероятно
    0.42
    疾患
    0.39
    манов
    0.39
     PAINE
    0.38
    ديث
    0.38
    临床
    0.38
    ভূত
    0.37
     Encu
    0.37
    Act Density 0.000%

    No Known Activations