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

    Neuronpedia

    INDEX
    Explanations

    circular diagram, Cinema EOS

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     COLOR
    0.45
    籀
    0.45
     VALID
    0.41
    蓥
    0.41
     صن
    0.40
    叁章
    0.39
    锒
    0.39
    垡
    0.39
     फोन
    0.38
     গাড়ীতে
    0.38
    POSITIVE LOGITS
     is
    0.46
     ہے۔
    0.38
    detail
    0.38
    ido
    0.37
    udi
    0.36
     necessary
    0.36
     freshwater
    0.36
     sostit
    0.36
     largely
    0.35
     nécessaire
    0.35
    Act Density 0.000%

    No Known Activations