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

    Neuronpedia

    INDEX
    Explanations

    AI alignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prepare
    0.41
     simplified
    0.41
     liberación
    0.41
     constitución
    0.40
    ostock
    0.40
     Julio
    0.40
     revitalize
    0.40
     introduce
    0.39
     exercised
    0.38
     ejerc
    0.38
    POSITIVE LOGITS
     कला
    0.49
    朊
    0.46
    נען
    0.46
    inkl
    0.46
     છ
    0.45
     bzw
    0.45
    issel
    0.45
     गड़ब
    0.44
     пла
    0.44
     миру
    0.44
    Act Density 0.010%

    No Known Activations