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

    Neuronpedia

    INDEX
    Explanations

    after "you"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rendimiento
    1.06
    ર
    0.98
    اب
    0.93
     gravitate
    0.93
     haga
    0.89
     atendimento
    0.89
    SB
    0.87
    培训
    0.87
     procesamiento
    0.86
     acuerdos
    0.86
    POSITIVE LOGITS
    i
    0.94
    a
    0.89
    <0x90>
    0.83
    ine
    0.80
    იშ
    0.78
    n
    0.78
    ið
    0.77
    ве
    0.76
     Doom
    0.75
    k
    0.74
    Act Density 0.000%

    No Known Activations